Performance for NVIDIA NeMo Retriever Embedding NIM#

To benchmark the performance of NVIDIA NeMo Retriever Embedding NIM, you can use the genai-perf tool. genai-perf is pre-installed in the Triton Server SDK container. For the remainder of this section, we will use genai-perf==0.0.11 that comes packaged with the Triton Server SDK 25.02.

To run a performance benchmark, first create a dataset of text examples that genai-perf can use when making requests to the embedding service. These examples should be representative of the type of data that you expect to receive in a production setting. The dataset should be formatted as a JSONL file where each line contains a {"text": ...} object, as shown in the following example.

Example#

Create a file named embeddings.jsonl that contains the following content.

{"text": "What was the first car ever driven?"}
{"text": "Who served as the 5th President of the United States of America?"}
{"text": "Is the Sydney Opera House located in Australia?"}
{"text": "In what state did they film Shrek 2?"}

Use the following example to run the Triton Inference Server SDK docker container. Mount the directory where you created your JSONL file, which appears as datasets/ in the following example.

export RELEASE="25.02"

docker run -it --rm \
  --gpus=all \
  --network="host" \
  --mount type=bind,source=${PWD}/datasets,target=/datasets \
  nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk

In the container, run the following command to run a performance benchmark by using the genai-perf command line tool.

genai-perf profile \
    -m nvidia/llama-nemotron-embed-vl-1b-v2 \
    --service-kind openai \
    --endpoint-type embeddings \
    --batch-size 2 \
    --input-file /datasets/embeddings.jsonl \
    --extra-inputs input_type:query \
    --extra-inputs truncate:END \
    --concurrency 5 \
    --url http://localhost:8000

You can see the full set of command line options for genai-perf in the Command Line Options section of the GenAI-Perf documentation.

Benchmarks#

All latency measurements are reported in milliseconds.

The VLM Embed benchmark tables report measurements for the supported GPU SKUs. For text rows, batch size is embedding inputs per request and throughput is embedding inputs per second. For image rows, batch size is images per request, image size is the generated JPEG resolution, and throughput is images per second.

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

2.3

2.3

2.4

2.4

352.8

query

20

1

3

4.1

4.3

4.4

4.4

628.0

query

20

1

5

4.1

4.3

4.4

4.5

1041.4

query

20

1

7

4.4

4.6

4.9

5.2

1316.6

query

20

1

9

4.4

4.4

4.6

4.6

1668.9

query

20

1

11

5.4

5.7

5.8

5.9

1699.0

query

20

1

13

4.6

4.7

4.9

5.1

2267.7

query

20

1

15

4.9

5.0

5.3

5.4

2421.9

passage

300

64

1

123.1

121.1

131.8

133.3

493.5

passage

300

64

3

349.6

353.4

361.5

364.8

534.4

passage

300

64

5

589.8

604.0

614.4

615.7

526.2

passage

512

64

1

195.7

195.6

198.0

198.7

317.9

passage

512

64

3

589.6

595.4

601.8

602.2

319.0

passage

512

64

5

1007.9

1024.3

1055.6

1058.9

309.1

image passage

336x336 JPEG

1

1

17.5

17.5

17.6

17.6

57.0

image passage

336x336 JPEG

1

2

29.5

29.5

29.7

29.8

34.1

image passage

336x336 JPEG

1

3

44.3

44.6

44.8

44.8

22.8

image passage

336x336 JPEG

1

5

73.4

74.8

74.9

75.0

14.1

image passage

336x336 JPEG

1

8

115.9

119.9

120.1

120.1

9.3

image passage

336x336 JPEG

4

1

63.3

63.3

63.5

63.6

63.2

image passage

336x336 JPEG

4

2

119.2

119.8

119.9

120.0

33.7

image passage

336x336 JPEG

4

3

178.5

180.2

180.4

180.4

22.7

image passage

336x336 JPEG

4

5

295.2

301.0

301.5

301.6

14.1

image passage

336x336 JPEG

4

8

466.1

482.9

483.3

483.4

9.4

image passage

336x336 JPEG

8

1

124.7

124.7

124.8

124.9

64.2

image passage

336x336 JPEG

8

2

239.9

241.0

241.3

241.4

33.5

image passage

336x336 JPEG

8

3

358.6

362.1

362.4

362.6

22.6

image passage

336x336 JPEG

8

5

592.7

604.4

605.4

607.0

14.0

image passage

336x336 JPEG

8

8

934.9

968.0

970.9

971.4

9.4

image passage

512x512 JPEG

1

1

17.7

17.7

17.9

17.9

56.4

image passage

512x512 JPEG

1

2

29.6

29.7

29.9

29.9

33.9

image passage

512x512 JPEG

1

3

44.4

44.8

45.0

45.0

22.7

image passage

512x512 JPEG

1

5

73.7

75.1

75.3

75.3

14.0

image passage

512x512 JPEG

1

8

116.5

120.4

120.7

120.8

9.3

image passage

512x512 JPEG

4

1

63.9

63.9

64.2

64.2

62.6

image passage

512x512 JPEG

4

2

119.6

120.1

120.4

120.4

33.6

image passage

512x512 JPEG

4

3

179.1

180.8

181.1

181.1

22.6

image passage

512x512 JPEG

4

5

296.3

302.1

302.4

302.4

14.0

image passage

512x512 JPEG

4

8

467.3

484.0

484.3

484.4

9.3

image passage

512x512 JPEG

8

1

126.0

125.9

126.5

126.6

63.5

image passage

512x512 JPEG

8

2

240.2

241.3

241.7

241.8

33.5

image passage

512x512 JPEG

8

3

359.3

362.7

363.1

363.2

22.6

image passage

512x512 JPEG

8

5

594.0

605.7

607.1

607.5

14.0

image passage

512x512 JPEG

8

8

936.8

970.1

971.4

972.0

9.3

image passage

1024x1024 JPEG

1

1

69.0

68.9

69.3

69.4

14.5

image passage

1024x1024 JPEG

1

2

130.6

131.2

131.5

131.6

7.7

image passage

1024x1024 JPEG

1

3

195.4

197.2

197.6

197.7

5.2

image passage

1024x1024 JPEG

1

5

323.1

329.4

329.9

330.5

3.2

image passage

1024x1024 JPEG

1

8

509.4

527.5

528.1

528.2

2.1

image passage

1024x1024 JPEG

4

1

272.3

271.2

277.1

279.1

14.7

image passage

1024x1024 JPEG

4

2

533.7

537.0

543.8

546.7

7.5

image passage

1024x1024 JPEG

4

3

798.0

809.6

818.3

819.6

5.1

image passage

1024x1024 JPEG

4

5

1322.1

1354.5

1371.0

1375.4

3.2

image passage

1024x1024 JPEG

4

8

2079.5

2159.9

2183.7

2186.3

2.1

image passage

1024x1024 JPEG

8

1

554.1

554.6

564.7

565.9

14.4

image passage

1024x1024 JPEG

8

2

1088.1

1096.3

1112.3

1113.3

7.4

image passage

1024x1024 JPEG

8

3

1628.1

1651.7

1664.9

1670.7

5.0

image passage

1024x1024 JPEG

8

5

2679.2

2740.7

2767.2

2776.2

3.1

image passage

1024x1024 JPEG

8

8

4225.0

4389.5

4426.5

4429.8

2.1

image passage

2048x2048 JPEG

1

1

70.5

70.5

71.1

71.2

14.2

image passage

2048x2048 JPEG

1

2

131.2

131.8

132.1

132.2

7.7

image passage

2048x2048 JPEG

1

3

196.4

198.3

198.7

198.8

5.2

image passage

2048x2048 JPEG

1

5

325.1

331.5

332.2

332.2

3.2

image passage

2048x2048 JPEG

1

8

512.0

530.3

530.8

530.9

2.1

image passage

2048x2048 JPEG

4

1

273.8

273.5

275.0

275.5

14.6

image passage

2048x2048 JPEG

4

2

524.3

526.3

530.9

531.6

7.7

image passage

2048x2048 JPEG

4

3

786.2

790.6

805.7

810.8

5.2

image passage

2048x2048 JPEG

4

5

1297.0

1319.6

1335.3

1337.6

3.2

image passage

2048x2048 JPEG

4

8

2045.1

2113.8

2135.7

2138.1

2.1

image passage

2048x2048 JPEG

8

1

550.1

548.1

559.5

563.8

14.5

image passage

2048x2048 JPEG

8

2

1060.5

1061.0

1087.1

1090.1

7.6

image passage

2048x2048 JPEG

8

3

1585.0

1592.0

1630.7

1633.7

5.1

image passage

2048x2048 JPEG

8

5

2617.5

2655.0

2724.0

2728.7

3.2

image passage

2048x2048 JPEG

8

8

4123.5

4248.4

4350.1

4357.3

2.1

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

2.6

2.6

2.6

2.6

312.1

query

20

1

3

4.6

4.6

4.7

4.8

558.7

query

20

1

5

4.7

4.7

4.9

5.0

903.9

query

20

1

7

4.7

4.8

4.9

5.1

1241.8

query

20

1

9

5.2

5.2

5.6

5.7

1420.7

query

20

1

11

5.1

5.1

5.5

5.9

1747.8

query

20

1

13

5.6

5.3

6.5

6.7

1922.1

query

20

1

15

6.8

6.9

7.2

8.6

1800.2

passage

300

64

1

117.9

117.9

118.4

118.6

507.5

passage

300

64

3

323.5

326.4

327.7

328.1

573.5

passage

300

64

5

538.5

548.9

550.5

550.8

573.5

passage

512

64

1

200.0

199.8

202.0

202.3

307.5

passage

512

64

3

567.7

573.0

575.8

576.7

329.9

passage

512

64

5

943.8

962.3

966.4

967.6

329.4

image passage

336x336 JPEG

1

1

20.1

20.1

20.2

20.3

49.8

image passage

336x336 JPEG

1

2

33.7

33.6

34.4

35.2

29.8

image passage

336x336 JPEG

1

3

50.7

51.0

51.2

51.8

19.9

image passage

336x336 JPEG

1

5

83.9

85.4

86.0

86.7

12.3

image passage

336x336 JPEG

1

8

132.8

137.4

137.5

137.5

8.1

image passage

336x336 JPEG

4

1

72.8

72.7

73.0

73.6

54.9

image passage

336x336 JPEG

4

2

136.3

136.8

137.3

138.4

29.5

image passage

336x336 JPEG

4

3

204.1

205.9

206.7

207.1

19.9

image passage

336x336 JPEG

4

5

337.8

344.3

345.1

346.0

12.3

image passage

336x336 JPEG

4

8

532.7

551.6

552.8

553.1

8.2

image passage

336x336 JPEG

8

1

143.0

142.8

143.3

143.9

55.9

image passage

336x336 JPEG

8

2

273.5

274.3

275.9

276.9

29.4

image passage

336x336 JPEG

8

3

409.3

412.3

413.4

418.7

19.8

image passage

336x336 JPEG

8

5

676.9

689.0

690.1

697.7

12.3

image passage

336x336 JPEG

8

8

1067.6

1103.6

1108.5

1125.1

8.2

image passage

512x512 JPEG

1

1

20.3

20.3

20.4

20.5

49.3

image passage

512x512 JPEG

1

2

33.6

33.7

34.0

34.1

29.9

image passage

512x512 JPEG

1

3

50.8

51.1

51.3

51.9

19.9

image passage

512x512 JPEG

1

5

84.3

85.8

85.9

86.5

12.3

image passage

512x512 JPEG

1

8

132.9

137.4

137.8

138.1

8.1

image passage

512x512 JPEG

4

1

73.7

73.6

74.2

75.5

54.3

image passage

512x512 JPEG

4

2

137.0

137.0

138.6

142.2

29.3

image passage

512x512 JPEG

4

3

204.5

206.2

207.6

208.4

19.8

image passage

512x512 JPEG

4

5

338.0

344.5

344.9

346.1

12.3

image passage

512x512 JPEG

4

8

533.6

552.3

554.2

554.9

8.2

image passage

512x512 JPEG

8

1

144.7

144.5

145.2

145.7

55.3

image passage

512x512 JPEG

8

2

274.1

274.7

276.3

277.1

29.3

image passage

512x512 JPEG

8

3

410.2

413.1

414.7

421.4

19.8

image passage

512x512 JPEG

8

5

677.5

689.9

692.2

698.3

12.3

image passage

512x512 JPEG

8

8

1069.3

1105.2

1109.3

1126.3

8.2

image passage

1024x1024 JPEG

1

1

77.1

77.1

77.7

77.7

13.0

image passage

1024x1024 JPEG

1

2

145.6

145.9

146.3

148.5

6.9

image passage

1024x1024 JPEG

1

3

217.3

219.3

219.6

219.9

4.7

image passage

1024x1024 JPEG

1

5

359.1

366.2

366.5

366.6

2.9

image passage

1024x1024 JPEG

1

8

566.5

586.7

587.2

587.3

1.9

image passage

1024x1024 JPEG

4

1

302.2

301.8

303.8

305.6

13.2

image passage

1024x1024 JPEG

4

2

584.0

586.0

588.7

591.5

6.9

image passage

1024x1024 JPEG

4

3

872.6

880.3

883.0

890.7

4.6

image passage

1024x1024 JPEG

4

5

1441.6

1468.0

1477.5

1486.2

2.9

image passage

1024x1024 JPEG

4

8

2271.5

2351.6

2362.9

2364.7

1.9

image passage

1024x1024 JPEG

8

1

601.6

600.7

603.5

607.0

13.3

image passage

1024x1024 JPEG

8

2

1166.9

1171.7

1176.8

1178.0

6.9

image passage

1024x1024 JPEG

8

3

1743.4

1759.6

1762.9

1769.8

4.7

image passage

1024x1024 JPEG

8

5

2881.6

2936.8

2952.5

2953.7

2.9

image passage

1024x1024 JPEG

8

8

4538.7

4699.2

4712.7

4714.2

1.9

image passage

2048x2048 JPEG

1

1

79.4

79.5

80.4

80.6

12.6

image passage

2048x2048 JPEG

1

2

146.4

146.5

147.7

151.6

6.9

image passage

2048x2048 JPEG

1

3

218.2

220.2

220.7

220.9

4.6

image passage

2048x2048 JPEG

1

5

361.4

368.4

369.0

369.3

2.9

image passage

2048x2048 JPEG

1

8

571.2

590.5

591.6

601.0

1.9

image passage

2048x2048 JPEG

4

1

310.7

310.4

312.7

313.7

12.9

image passage

2048x2048 JPEG

4

2

584.8

586.8

589.1

590.4

6.9

image passage

2048x2048 JPEG

4

3

875.5

883.1

885.8

888.2

4.6

image passage

2048x2048 JPEG

4

5

1447.2

1475.0

1476.9

1491.8

2.9

image passage

2048x2048 JPEG

4

8

2282.4

2363.7

2366.4

2367.1

1.9

image passage

2048x2048 JPEG

8

1

619.6

618.6

625.5

626.1

12.9

image passage

2048x2048 JPEG

8

2

1170.0

1174.1

1179.5

1181.6

6.9

image passage

2048x2048 JPEG

8

3

1749.5

1765.4

1770.5

1773.4

4.6

image passage

2048x2048 JPEG

8

5

2897.2

2952.6

2963.6

2966.9

2.9

image passage

2048x2048 JPEG

8

8

4576.9

4738.8

4749.0

4752.8

1.9

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

2.6

2.5

2.7

2.7

249.4

query

20

1

3

4.1

4.4

4.8

5.0

524.8

query

20

1

5

4.4

4.5

6.3

7.0

833.4

query

20

1

7

4.7

4.6

6.2

9.0

1093.6

query

20

1

9

5.5

5.2

8.6

8.9

1284.3

query

20

1

11

5.5

5.2

10.1

11.5

1478.0

query

20

1

13

5.6

5.3

7.9

8.1

1679.9

query

20

1

15

6.2

6.1

8.9

10.6

1873.0

passage

300

64

1

149.6

149.6

150.1

150.5

408.9

passage

300

64

3

422.2

426.1

427.1

427.6

443.0

passage

300

64

5

701.0

714.9

716.4

716.5

443.0

passage

512

64

1

361.2

360.7

365.6

367.3

173.8

passage

512

64

3

1049.8

1059.5

1067.8

1068.7

179.8

passage

512

64

5

1736.6

1771.6

1782.3

1784.5

179.8

image passage

336x336 JPEG

1

1

18.5

17.4

17.5

25.3

55.7

image passage

336x336 JPEG

1

2

27.9

26.9

27.4

34.0

36.5

image passage

336x336 JPEG

1

3

42.0

41.3

45.5

50.2

24.1

image passage

336x336 JPEG

1

5

69.9

70.0

70.9

77.0

14.8

image passage

336x336 JPEG

1

8

114.4

113.1

139.6

142.4

9.5

image passage

336x336 JPEG

4

1

62.5

60.9

63.3

71.7

64.4

image passage

336x336 JPEG

4

2

113.4

111.9

124.6

127.2

35.5

image passage

336x336 JPEG

4

3

171.2

169.0

185.6

188.4

23.7

image passage

336x336 JPEG

4

5

285.5

283.4

305.0

307.6

14.6

image passage

336x336 JPEG

4

8

454.3

469.6

481.9

482.3

9.4

image passage

336x336 JPEG

8

1

121.1

118.6

130.7

135.2

66.2

image passage

336x336 JPEG

8

2

231.4

225.8

251.6

257.7

34.8

image passage

336x336 JPEG

8

3

347.6

343.0

372.0

378.9

23.4

image passage

336x336 JPEG

8

5

574.6

583.0

603.7

614.8

14.5

image passage

336x336 JPEG

8

8

901.2

926.7

955.7

960.4

9.7

image passage

512x512 JPEG

1

1

18.0

17.5

17.7

18.6

56.1

image passage

512x512 JPEG

1

2

27.6

27.2

27.5

28.5

36.5

image passage

512x512 JPEG

1

3

41.9

41.3

41.7

52.4

24.2

image passage

512x512 JPEG

1

5

73.6

69.9

85.6

95.4

14.2

image passage

512x512 JPEG

1

8

110.6

112.7

113.7

131.6

9.8

image passage

512x512 JPEG

4

1

63.0

61.4

70.5

73.5

63.8

image passage

512x512 JPEG

4

2

114.6

112.2

126.1

127.5

35.2

image passage

512x512 JPEG

4

3

173.0

169.3

190.2

193.3

23.5

image passage

512x512 JPEG

4

5

283.4

283.6

298.0

304.7

14.5

image passage

512x512 JPEG

4

8

452.2

459.4

490.2

518.2

9.7

image passage

512x512 JPEG

8

1

123.3

120.2

133.5

138.6

65.1

image passage

512x512 JPEG

8

2

231.1

226.0

242.0

246.2

34.8

image passage

512x512 JPEG

8

3

344.3

341.2

359.2

362.7

23.6

image passage

512x512 JPEG

8

5

571.6

582.6

601.6

605.3

14.6

image passage

512x512 JPEG

8

8

903.2

933.5

941.6

948.8

9.7

image passage

1024x1024 JPEG

1

1

89.0

87.0

87.8

104.4

11.3

image passage

1024x1024 JPEG

1

2

165.9

164.8

166.7

175.2

6.1

image passage

1024x1024 JPEG

1

3

247.7

247.7

251.0

270.0

4.1

image passage

1024x1024 JPEG

1

5

409.8

414.4

432.3

438.5

2.5

image passage

1024x1024 JPEG

1

8

642.3

663.7

667.1

676.7

1.7

image passage

1024x1024 JPEG

4

1

343.2

339.6

356.0

363.0

11.7

image passage

1024x1024 JPEG

4

2

662.6

663.2

670.1

680.4

6.1

image passage

1024x1024 JPEG

4

3

997.8

996.5

1033.5

1041.3

4.1

image passage

1024x1024 JPEG

4

5

1642.2

1668.1

1701.8

1714.4

2.5

image passage

1024x1024 JPEG

4

8

2591.9

2671.7

2707.8

2771.5

1.7

image passage

1024x1024 JPEG

8

1

683.2

677.5

698.8

704.3

11.7

image passage

1024x1024 JPEG

8

2

1333.9

1331.0

1369.9

1381.8

6.0

image passage

1024x1024 JPEG

8

3

1987.5

1998.3

2044.4

2058.4

4.1

image passage

1024x1024 JPEG

8

5

3288.4

3342.0

3391.1

3423.1

2.5

image passage

1024x1024 JPEG

8

8

5184.3

5368.9

5411.5

5448.4

1.7

image passage

2048x2048 JPEG

1

1

88.6

87.6

89.4

100.6

11.3

image passage

2048x2048 JPEG

1

2

163.4

161.7

171.3

179.5

6.2

image passage

2048x2048 JPEG

1

3

245.1

243.6

260.1

260.6

4.1

image passage

2048x2048 JPEG

1

5

406.1

407.6

425.4

426.5

2.6

image passage

2048x2048 JPEG

1

8

639.7

660.4

669.9

686.7

1.7

image passage

2048x2048 JPEG

4

1

343.4

340.5

352.8

362.2

11.7

image passage

2048x2048 JPEG

4

2

660.5

665.7

673.2

688.2

6.1

image passage

2048x2048 JPEG

4

3

988.0

995.9

1005.8

1020.3

4.1

image passage

2048x2048 JPEG

4

5

1629.1

1663.9

1677.2

1694.1

2.6

image passage

2048x2048 JPEG

4

8

2567.7

2662.8

2672.1

2684.2

1.7

image passage

2048x2048 JPEG

8

1

684.9

678.8

700.5

706.7

11.7

image passage

2048x2048 JPEG

8

2

1321.7

1322.9

1346.3

1359.7

6.1

image passage

2048x2048 JPEG

8

3

1972.1

1991.7

2004.8

2022.1

4.1

image passage

2048x2048 JPEG

8

5

3261.1

3320.0

3352.2

3384.5

2.6

image passage

2048x2048 JPEG

8

8

5137.7

5319.9

5338.2

5344.2

1.7

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

1.8

1.8

1.9

1.9

426.9

query

20

1

3

2.6

2.3

3.8

3.8

935.5

query

20

1

5

3.6

3.8

4.4

4.5

1159.1

query

20

1

7

4.1

4.0

5.6

5.8

1438.4

query

20

1

9

4.3

4.4

5.7

5.9

1747.4

query

20

1

11

5.2

4.6

7.1

7.2

1786.2

query

20

1

13

4.6

4.5

6.0

6.1

2320.9

query

20

1

15

4.7

5.0

6.0

6.4

2596.1

passage

300

64

1

139.9

139.9

140.5

140.8

439.8

passage

300

64

3

399.1

402.8

404.3

404.6

469.5

passage

300

64

5

662.2

675.4

677.2

677.5

469.5

passage

512

64

1

334.0

333.6

337.4

338.3

188.4

passage

512

64

3

975.0

984.4

990.0

991.3

193.8

passage

512

64

5

1612.3

1645.1

1652.2

1653.5

193.8

image passage

336x336 JPEG

1

1

22.3

21.7

21.8

22.5

45.4

image passage

336x336 JPEG

1

2

37.9

38.0

38.1

38.6

26.5

image passage

336x336 JPEG

1

3

56.7

57.2

57.2

57.3

17.8

image passage

336x336 JPEG

1

5

93.8

95.6

95.7

95.8

11.0

image passage

336x336 JPEG

1

8

149.4

153.1

156.5

170.9

7.3

image passage

336x336 JPEG

4

1

81.2

79.8

80.2

89.0

49.5

image passage

336x336 JPEG

4

2

153.7

153.1

153.4

166.3

26.2

image passage

336x336 JPEG

4

3

231.0

229.9

247.2

248.6

17.6

image passage

336x336 JPEG

4

5

378.8

383.7

389.9

400.1

11.0

image passage

336x336 JPEG

4

8

604.4

615.6

642.8

657.9

7.2

image passage

336x336 JPEG

8

1

160.1

158.0

162.0

174.7

50.1

image passage

336x336 JPEG

8

2

310.4

307.7

322.6

336.0

25.9

image passage

336x336 JPEG

8

3

464.4

461.9

483.5

512.2

17.5

image passage

336x336 JPEG

8

5

767.4

772.0

823.1

830.1

10.9

image passage

336x336 JPEG

8

8

1208.0

1235.9

1298.0

1307.0

7.3

image passage

512x512 JPEG

1

1

22.4

21.7

21.9

24.3

45.1

image passage

512x512 JPEG

1

2

39.1

37.9

38.4

50.6

25.9

image passage

512x512 JPEG

1

3

57.0

57.4

57.6

58.2

17.7

image passage

512x512 JPEG

1

5

94.1

95.7

95.9

97.2

11.0

image passage

512x512 JPEG

1

8

148.3

153.4

153.7

153.9

7.3

image passage

512x512 JPEG

4

1

81.8

80.4

82.7

94.1

49.0

image passage

512x512 JPEG

4

2

155.9

153.2

166.4

177.9

25.8

image passage

512x512 JPEG

4

3

230.4

230.5

231.4

248.9

17.6

image passage

512x512 JPEG

4

5

380.7

385.0

390.2

408.5

10.9

image passage

512x512 JPEG

4

8

605.2

616.2

657.1

677.5

7.3

image passage

512x512 JPEG

8

1

161.8

159.4

163.2

174.3

49.6

image passage

512x512 JPEG

8

2

310.7

307.4

322.0

348.5

25.9

image passage

512x512 JPEG

8

3

464.8

462.5

484.0

510.1

17.5

image passage

512x512 JPEG

8

5

766.0

772.5

810.1

821.0

10.9

image passage

512x512 JPEG

8

8

1210.6

1238.3

1299.0

1304.6

7.2

image passage

1024x1024 JPEG

1

1

109.8

108.4

108.9

113.4

9.1

image passage

1024x1024 JPEG

1

2

211.1

210.0

210.9

216.3

4.8

image passage

1024x1024 JPEG

1

3

314.1

315.3

322.3

329.1

3.2

image passage

1024x1024 JPEG

1

5

520.3

525.7

549.1

554.9

2.0

image passage

1024x1024 JPEG

1

8

823.4

842.5

892.1

897.7

1.3

image passage

1024x1024 JPEG

4

1

433.7

428.0

452.5

474.8

9.2

image passage

1024x1024 JPEG

4

2

846.5

846.1

868.6

871.0

4.7

image passage

1024x1024 JPEG

4

3

1265.0

1268.4

1305.0

1309.4

3.2

image passage

1024x1024 JPEG

4

5

2085.6

2117.9

2151.5

2157.8

2.0

image passage

1024x1024 JPEG

4

8

3292.2

3410.4

3433.6

3437.2

1.3

image passage

1024x1024 JPEG

8

1

864.3

855.6

890.3

897.4

9.3

image passage

1024x1024 JPEG

8

2

1693.5

1695.3

1723.9

1727.6

4.7

image passage

1024x1024 JPEG

8

3

2531.1

2555.8

2579.4

2583.6

3.2

image passage

1024x1024 JPEG

8

5

4184.7

4270.2

4287.7

4296.9

2.0

image passage

1024x1024 JPEG

8

8

6578.8

6813.0

6838.2

6845.4

1.3

image passage

2048x2048 JPEG

1

1

110.9

109.9

110.7

116.1

9.0

image passage

2048x2048 JPEG

1

2

211.0

210.3

214.5

226.4

4.8

image passage

2048x2048 JPEG

1

3

316.6

315.9

327.4

343.1

3.2

image passage

2048x2048 JPEG

1

5

520.8

527.1

547.1

548.6

2.0

image passage

2048x2048 JPEG

1

8

822.8

845.6

872.5

875.1

1.3

image passage

2048x2048 JPEG

4

1

437.5

434.4

449.5

453.0

9.1

image passage

2048x2048 JPEG

4

2

850.9

848.4

874.0

877.0

4.7

image passage

2048x2048 JPEG

4

3

1265.7

1272.8

1288.3

1293.9

3.2

image passage

2048x2048 JPEG

4

5

2091.5

2132.9

2155.0

2158.8

2.0

image passage

2048x2048 JPEG

4

8

3299.6

3419.2

3439.6

3444.4

1.3

image passage

2048x2048 JPEG

8

1

876.0

870.1

891.7

898.0

9.1

image passage

2048x2048 JPEG

8

2

1699.3

1706.7

1722.6

1727.6

4.7

image passage

2048x2048 JPEG

8

3

2535.9

2558.4

2580.8

2586.6

3.2

image passage

2048x2048 JPEG

8

5

4176.6

4253.3

4296.1

4305.1

2.0

image passage

2048x2048 JPEG

8

8

6584.1

6816.2

6852.1

6862.0

1.3

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

3.0

3.0

3.1

3.1

225.7

query

20

1

3

4.5

4.8

5.6

5.7

489.2

query

20

1

5

5.6

4.8

9.4

11.1

690.3

query

20

1

7

7.7

5.5

14.5

15.5

742.8

query

20

1

9

6.7

5.7

10.4

11.9

1057.9

query

20

1

11

7.2

5.6

16.3

17.0

1236.9

query

20

1

13

9.4

9.1

17.2

17.5

1137.7

query

20

1

15

9.9

8.3

15.2

15.4

1261.1

passage

300

64

1

71.0

70.8

72.3

72.6

816.9

passage

300

64

3

189.9

191.6

193.1

194.2

962.6

passage

300

64

5

318.3

324.5

326.5

326.8

962.1

passage

512

64

1

121.0

121.1

122.1

122.4

497.5

passage

512

64

3

338.7

341.6

344.4

344.7

548.7

passage

512

64

5

564.9

575.9

581.0

581.7

547.7

image passage

336x336 JPEG

1

1

17.2

17.0

17.1

17.2

58.2

image passage

336x336 JPEG

1

2

26.4

26.3

26.6

26.7

38.0

image passage

336x336 JPEG

1

3

40.7

40.1

44.1

47.7

24.9

image passage

336x336 JPEG

1

5

68.6

68.0

77.0

78.9

15.1

image passage

336x336 JPEG

1

8

107.7

109.7

119.1

119.3

10.0

image passage

336x336 JPEG

4

1

60.0

59.4

59.6

64.7

66.8

image passage

336x336 JPEG

4

2

112.0

109.3

120.8

124.1

36.0

image passage

336x336 JPEG

4

3

165.0

164.8

175.4

176.8

24.6

image passage

336x336 JPEG

4

5

276.1

276.9

289.4

290.8

15.0

image passage

336x336 JPEG

4

8

434.0

445.0

459.4

460.5

10.1

image passage

336x336 JPEG

8

1

117.8

115.9

126.0

130.3

68.0

image passage

336x336 JPEG

8

2

222.3

220.1

231.5

232.8

36.2

image passage

336x336 JPEG

8

3

334.0

332.9

343.2

348.1

24.3

image passage

336x336 JPEG

8

5

550.8

562.5

567.7

571.5

15.1

image passage

336x336 JPEG

8

8

868.7

899.8

904.9

907.0

10.1

image passage

512x512 JPEG

1

1

17.4

17.2

17.4

17.4

57.7

image passage

512x512 JPEG

1

2

26.8

26.3

26.7

31.7

37.6

image passage

512x512 JPEG

1

3

40.6

40.2

41.1

46.8

24.9

image passage

512x512 JPEG

1

5

68.5

68.1

76.8

78.8

15.1

image passage

512x512 JPEG

1

8

109.0

110.2

121.5

129.9

9.9

image passage

512x512 JPEG

4

1

60.9

60.1

60.7

65.9

65.9

image passage

512x512 JPEG

4

2

110.3

109.4

114.6

120.3

36.4

image passage

512x512 JPEG

4

3

165.8

165.3

173.8

174.1

24.4

image passage

512x512 JPEG

4

5

274.2

276.0

287.6

287.8

15.0

image passage

512x512 JPEG

4

8

440.3

453.0

468.1

496.9

9.9

image passage

512x512 JPEG

8

1

119.1

117.4

123.9

129.1

67.3

image passage

512x512 JPEG

8

2

222.1

220.5

231.0

232.2

36.2

image passage

512x512 JPEG

8

3

333.5

332.4

345.0

347.5

24.3

image passage

512x512 JPEG

8

5

551.5

563.6

570.0

574.1

15.0

image passage

512x512 JPEG

8

8

870.9

899.7

902.0

941.1

10.1

image passage

1024x1024 JPEG

1

1

63.0

62.4

62.8

64.8

15.9

image passage

1024x1024 JPEG

1

2

115.3

115.3

119.2

120.5

8.7

image passage

1024x1024 JPEG

1

3

172.5

173.5

178.4

178.7

5.9

image passage

1024x1024 JPEG

1

5

285.7

290.6

293.6

294.7

3.6

image passage

1024x1024 JPEG

1

8

450.3

466.2

466.9

466.9

2.4

image passage

1024x1024 JPEG

4

1

242.6

240.7

242.7

253.8

16.5

image passage

1024x1024 JPEG

4

2

466.3

465.5

471.9

472.6

8.6

image passage

1024x1024 JPEG

4

3

697.4

702.8

705.3

705.8

5.8

image passage

1024x1024 JPEG

4

5

1152.7

1171.4

1182.0

1188.1

3.6

image passage

1024x1024 JPEG

4

8

1818.0

1879.6

1885.2

1940.0

2.4

image passage

1024x1024 JPEG

8

1

482.0

479.4

488.5

490.7

16.6

image passage

1024x1024 JPEG

8

2

933.9

936.5

938.7

955.2

8.6

image passage

1024x1024 JPEG

8

3

1394.4

1405.3

1411.6

1422.5

5.8

image passage

1024x1024 JPEG

8

5

2309.2

2346.5

2395.0

2413.7

3.6

image passage

1024x1024 JPEG

8

8

3631.9

3760.2

3768.9

3817.7

2.4

image passage

2048x2048 JPEG

1

1

64.8

64.5

65.2

65.3

15.5

image passage

2048x2048 JPEG

1

2

115.7

115.6

116.1

117.1

8.7

image passage

2048x2048 JPEG

1

3

173.0

174.5

175.0

175.8

5.8

image passage

2048x2048 JPEG

1

5

287.8

292.3

295.9

299.7

3.6

image passage

2048x2048 JPEG

1

8

455.1

469.1

471.8

490.2

2.4

image passage

2048x2048 JPEG

4

1

250.5

248.7

252.9

261.8

16.0

image passage

2048x2048 JPEG

4

2

467.3

466.4

473.3

481.7

8.6

image passage

2048x2048 JPEG

4

3

700.9

703.0

723.5

732.6

5.8

image passage

2048x2048 JPEG

4

5

1162.2

1174.6

1215.4

1221.7

3.6

image passage

2048x2048 JPEG

4

8

1825.3

1882.2

1902.1

1970.5

2.4

image passage

2048x2048 JPEG

8

1

498.5

495.8

510.4

514.5

16.1

image passage

2048x2048 JPEG

8

2

935.0

933.8

949.8

975.7

8.6

image passage

2048x2048 JPEG

8

3

1395.8

1402.2

1433.3

1467.3

5.8

image passage

2048x2048 JPEG

8

5

2307.1

2348.7

2368.9

2382.3

3.6

image passage

2048x2048 JPEG

8

8

3647.7

3759.5

3838.6

3852.8

2.4

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

3.3

3.3

3.6

3.7

245.3

query

20

1

3

5.4

5.4

5.7

5.7

474.4

query

20

1

5

6.5

6.4

6.7

6.8

669.8

query

20

1

7

7.2

7.1

7.8

8.5

815.5

query

20

1

9

7.4

7.3

8.3

8.4

1026.8

query

20

1

11

10.4

10.7

11.0

11.1

917.6

query

20

1

13

8.7

8.8

9.3

10.4

1253.7

query

20

1

15

9.3

9.3

11.1

11.2

1352.2

passage

300

64

1

381.9

382.0

383.4

383.8

164.0

passage

300

64

3

1105.8

1116.4

1119.7

1120.8

170.6

passage

300

64

5

1832.3

1869.4

1873.3

1873.8

170.4

passage

512

64

1

838.4

837.7

846.2

848.1

75.5

passage

512

64

3

2463.4

2488.3

2500.3

2503.0

76.9

passage

512

64

5

4071.6

4153.5

4170.1

4175.1

76.9

image passage

336x336 JPEG

1

1

37.7

34.3

43.9

47.2

26.9

image passage

336x336 JPEG

1

2

69.9

66.9

79.1

82.2

14.5

image passage

336x336 JPEG

1

3

105.8

103.3

119.7

124.9

9.7

image passage

336x336 JPEG

1

5

172.0

172.1

191.0

195.3

6.0

image passage

336x336 JPEG

1

8

272.7

279.7

301.9

305.0

4.0

image passage

336x336 JPEG

4

1

143.7

140.2

158.7

162.4

28.0

image passage

336x336 JPEG

4

2

280.6

280.9

303.9

307.0

14.3

image passage

336x336 JPEG

4

3

420.6

422.8

439.0

443.9

9.6

image passage

336x336 JPEG

4

5

694.6

706.6

727.9

730.9

5.9

image passage

336x336 JPEG

4

8

1093.9

1128.7

1148.4

1150.3

3.9

image passage

336x336 JPEG

8

1

288.0

288.5

307.3

309.1

27.8

image passage

336x336 JPEG

8

2

562.2

564.9

574.3

584.1

14.3

image passage

336x336 JPEG

8

3

840.2

848.4

871.9

873.1

9.7

image passage

336x336 JPEG

8

5

1390.4

1419.2

1439.5

1447.7

6.0

image passage

336x336 JPEG

8

8

2184.5

2262.3

2278.7

2285.0

4.0

image passage

512x512 JPEG

1

1

37.3

34.5

42.1

43.7

27.1

image passage

512x512 JPEG

1

2

69.8

65.7

79.6

85.0

14.5

image passage

512x512 JPEG

1

3

105.0

101.2

118.4

123.9

9.8

image passage

512x512 JPEG

1

5

171.9

169.8

195.5

197.8

6.1

image passage

512x512 JPEG

1

8

276.9

283.3

309.8

316.2

3.9

image passage

512x512 JPEG

4

1

142.7

139.3

156.5

162.2

28.2

image passage

512x512 JPEG

4

2

281.0

284.0

302.7

306.0

14.3

image passage

512x512 JPEG

4

3

420.2

424.7

437.6

440.9

9.6

image passage

512x512 JPEG

4

5

693.8

701.3

728.8

731.7

6.0

image passage

512x512 JPEG

4

8

1093.0

1131.7

1140.0

1145.5

4.0

image passage

512x512 JPEG

8

1

290.0

291.5

312.0

314.0

27.7

image passage

512x512 JPEG

8

2

562.7

565.3

575.4

581.1

14.3

image passage

512x512 JPEG

8

3

839.6

850.2

866.6

868.1

9.7

image passage

512x512 JPEG

8

5

1386.4

1414.2

1437.8

1441.3

6.0

image passage

512x512 JPEG

8

8

2182.3

2261.9

2282.9

2290.4

4.0

image passage

1024x1024 JPEG

1

1

215.2

194.8

206.4

224.3

5.1

image passage

1024x1024 JPEG

1

2

376.7

376.2

394.7

399.2

2.7

image passage

1024x1024 JPEG

1

3

563.2

569.3

580.9

589.7

1.8

image passage

1024x1024 JPEG

1

5

932.8

950.6

967.0

973.3

1.1

image passage

1024x1024 JPEG

1

8

1472.2

1521.6

1548.8

1557.3

0.7

image passage

1024x1024 JPEG

4

1

764.6

765.3

784.2

788.2

5.2

image passage

1024x1024 JPEG

4

2

1512.8

1519.0

1546.4

1550.2

2.7

image passage

1024x1024 JPEG

4

3

2259.7

2280.7

2308.4

2313.8

1.8

image passage

1024x1024 JPEG

4

5

3735.3

3807.6

3836.4

3846.5

1.1

image passage

1024x1024 JPEG

4

8

5882.5

6088.6

6136.9

6145.3

0.7

image passage

1024x1024 JPEG

8

1

1532.2

1531.4

1548.9

1562.8

5.2

image passage

1024x1024 JPEG

8

2

3026.4

3044.2

3070.3

3076.5

2.7

image passage

1024x1024 JPEG

8

3

4518.2

4562.2

4588.5

4603.9

1.8

image passage

1024x1024 JPEG

8

5

7448.2

7595.0

7640.3

7649.3

1.1

image passage

1024x1024 JPEG

8

8

11746.7

12167.5

12202.4

12208.9

0.7

image passage

2048x2048 JPEG

1

1

190.9

192.7

202.4

205.9

5.2

image passage

2048x2048 JPEG

1

2

377.5

377.8

392.9

394.8

2.7

image passage

2048x2048 JPEG

1

3

561.5

563.8

578.8

593.8

1.8

image passage

2048x2048 JPEG

1

5

931.6

949.6

969.1

975.7

1.1

image passage

2048x2048 JPEG

1

8

1466.4

1521.4

1538.8

1540.7

0.8

image passage

2048x2048 JPEG

4

1

770.8

773.5

783.6

787.2

5.2

image passage

2048x2048 JPEG

4

2

1512.0

1520.9

1539.9

1544.3

2.7

image passage

2048x2048 JPEG

4

3

2261.7

2282.7

2305.3

2312.0

1.8

image passage

2048x2048 JPEG

4

5

3732.2

3804.0

3837.9

3845.6

1.1

image passage

2048x2048 JPEG

4

8

5895.7

6102.5

6145.4

6153.3

0.7

image passage

2048x2048 JPEG

8

1

1541.6

1541.3

1563.5

1570.8

5.2

image passage

2048x2048 JPEG

8

2

3017.7

3034.2

3061.5

3067.3

2.7

image passage

2048x2048 JPEG

8

3

4507.2

4550.4

4581.2

4589.9

1.8

image passage

2048x2048 JPEG

8

5

7445.9

7591.7

7622.3

7632.9

1.1

image passage

2048x2048 JPEG

8

8

11960.2

12184.1

12272.2

14723.2

0.7

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

2.4

2.4

2.5

2.5

322.8

query

20

1

3

4.2

4.3

5.2

8.4

616.4

query

20

1

5

5.1

4.5

5.5

6.7

856.9

query

20

1

7

6.8

5.3

13.9

15.2

899.9

query

20

1

9

7.1

5.4

12.2

17.6

1087.3

query

20

1

11

5.9

5.2

8.7

8.9

1514.1

query

20

1

13

7.2

5.9

15.6

16.0

1540.9

query

20

1

15

6.3

6.7

8.3

8.4

1958.3

passage

300

64

1

97.7

97.4

99.4

99.9

609.7

passage

300

64

3

272.8

275.5

277.3

278.9

677.8

passage

300

64

5

455.4

464.7

467.1

467.6

677.9

passage

512

64

1

168.1

168.0

169.3

169.7

364.9

passage

512

64

3

483.8

488.4

490.9

491.3

387.0

passage

512

64

5

804.7

820.9

825.2

825.9

386.1

image passage

336x336 JPEG

1

1

18.0

18.0

18.1

18.1

55.6

image passage

336x336 JPEG

1

2

29.6

29.7

29.8

29.8

33.9

image passage

336x336 JPEG

1

3

44.4

44.8

44.8

44.9

22.7

image passage

336x336 JPEG

1

5

74.2

75.5

75.6

76.2

13.9

image passage

336x336 JPEG

1

8

117.2

121.1

121.2

122.3

9.2

image passage

336x336 JPEG

4

1

64.8

64.7

64.9

65.0

61.8

image passage

336x336 JPEG

4

2

120.3

120.7

121.0

121.2

33.4

image passage

336x336 JPEG

4

3

180.2

181.9

182.1

182.2

22.5

image passage

336x336 JPEG

4

5

298.8

304.1

306.0

306.6

13.9

image passage

336x336 JPEG

4

8

511.4

488.3

505.2

981.6

8.9

image passage

336x336 JPEG

8

1

127.2

127.3

127.5

127.6

62.9

image passage

336x336 JPEG

8

2

242.3

243.5

243.7

243.7

33.2

image passage

336x336 JPEG

8

3

387.0

366.5

367.7

368.8

21.8

image passage

336x336 JPEG

8

5

639.7

612.6

615.5

707.0

13.5

image passage

336x336 JPEG

8

8

1010.8

982.1

985.0

1762.6

8.9

image passage

512x512 JPEG

1

1

18.2

18.2

18.3

18.3

55.0

image passage

512x512 JPEG

1

2

29.6

29.6

29.7

29.8

33.9

image passage

512x512 JPEG

1

3

44.4

44.8

44.8

44.9

22.7

image passage

512x512 JPEG

1

5

74.2

75.5

75.7

75.7

13.9

image passage

512x512 JPEG

1

8

117.7

121.6

121.9

122.6

9.2

image passage

512x512 JPEG

4

1

65.4

65.4

65.6

65.7

61.2

image passage

512x512 JPEG

4

2

135.9

120.8

121.3

123.4

32.6

image passage

512x512 JPEG

4

3

181.0

182.1

183.0

187.9

22.4

image passage

512x512 JPEG

4

5

299.2

304.8

306.1

306.2

13.9

image passage

512x512 JPEG

4

8

506.6

489.6

493.2

906.2

8.9

image passage

512x512 JPEG

8

1

128.7

128.6

129.0

129.4

62.2

image passage

512x512 JPEG

8

2

251.1

244.0

245.6

248.4

32.7

image passage

512x512 JPEG

8

3

364.0

367.0

367.7

371.4

22.3

image passage

512x512 JPEG

8

5

624.2

613.4

632.1

668.1

13.5

image passage

512x512 JPEG

8

8

950.1

983.4

987.0

994.3

9.2

image passage

1024x1024 JPEG

1

1

70.4

70.2

70.9

71.9

14.2

image passage

1024x1024 JPEG

1

2

139.9

131.5

132.6

134.7

7.5

image passage

1024x1024 JPEG

1

3

196.4

198.2

198.5

199.1

5.2

image passage

1024x1024 JPEG

1

5

324.9

331.1

332.3

333.0

3.2

image passage

1024x1024 JPEG

1

8

512.7

530.9

531.4

531.5

2.1

image passage

1024x1024 JPEG

4

1

281.1

272.8

273.5

274.7

14.5

image passage

1024x1024 JPEG

4

2

552.8

530.1

532.5

539.5

7.5

image passage

1024x1024 JPEG

4

3

827.0

796.5

806.4

1140.9

5.0

image passage

1024x1024 JPEG

4

5

1347.0

1329.7

1332.0

1382.4

3.1

image passage

1024x1024 JPEG

4

8

2122.7

2128.9

2134.3

2989.9

2.1

image passage

1024x1024 JPEG

8

1

563.1

542.8

544.8

546.7

14.5

image passage

1024x1024 JPEG

8

2

1088.2

1064.9

1077.0

1101.7

7.5

image passage

1024x1024 JPEG

8

3

1644.9

1599.6

1613.2

2350.2

5.0

image passage

1024x1024 JPEG

8

5

2722.2

2669.0

3152.7

3508.9

3.1

image passage

1024x1024 JPEG

8

8

4283.4

4263.1

5069.3

5133.6

2.1

image passage

2048x2048 JPEG

1

1

80.5

72.3

73.3

73.9

13.6

image passage

2048x2048 JPEG

1

2

131.5

131.8

133.4

134.0

7.6

image passage

2048x2048 JPEG

1

3

197.1

198.9

199.5

199.8

5.1

image passage

2048x2048 JPEG

1

5

391.4

333.5

682.2

762.1

3.0

image passage

2048x2048 JPEG

1

8

516.3

534.4

535.4

535.9

2.1

image passage

2048x2048 JPEG

4

1

292.6

280.0

281.9

283.1

14.1

image passage

2048x2048 JPEG

4

2

545.0

530.1

532.4

533.1

7.5

image passage

2048x2048 JPEG

4

3

818.1

799.3

802.3

815.1

5.0

image passage

2048x2048 JPEG

4

5

1352.5

1336.8

1342.1

1394.2

3.1

image passage

2048x2048 JPEG

4

8

2137.4

2144.8

2151.3

2986.1

2.1

image passage

2048x2048 JPEG

8

1

579.0

558.2

562.1

567.6

14.1

image passage

2048x2048 JPEG

8

2

1101.7

1063.5

1069.2

1484.1

7.4

image passage

2048x2048 JPEG

8

3

1650.1

1600.1

1661.8

2153.5

5.0

image passage

2048x2048 JPEG

8

5

2727.4

2676.4

3111.1

3512.9

3.1

image passage

2048x2048 JPEG

8

8

4316.8

4293.0

5152.2

5171.9

2.0

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

2.5

2.4

2.5

2.5

316.9

query

20

1

3

4.6

3.6

5.4

14.6

551.8

query

20

1

5

6.1

4.5

11.6

14.2

718.2

query

20

1

7

7.4

6.3

14.6

16.8

839.0

query

20

1

9

5.1

5.3

5.6

7.1

1444.0

query

20

1

11

6.9

5.4

14.2

14.4

1358.0

query

20

1

13

6.5

5.5

13.2

14.7

1672.4

query

20

1

15

7.5

7.1

11.6

11.7

1693.4

passage

300

64

1

72.4

72.2

73.6

74.2

796.8

passage

300

64

3

195.1

196.7

198.6

199.9

936.1

passage

300

64

5

328.3

333.6

337.9

343.7

932.3

passage

512

64

1

123.4

123.5

124.7

124.7

487.2

passage

512

64

3

347.6

351.2

352.8

354.2

534.3

passage

512

64

5

578.9

590.3

594.2

595.2

534.3

image passage

336x336 JPEG

1

1

17.0

17.0

17.1

17.1

58.9

image passage

336x336 JPEG

1

2

28.2

28.2

28.3

28.3

35.6

image passage

336x336 JPEG

1

3

42.3

42.7

42.7

42.7

23.9

image passage

336x336 JPEG

1

5

70.3

71.6

71.9

72.4

14.7

image passage

336x336 JPEG

1

8

111.2

115.0

115.3

115.5

9.7

image passage

336x336 JPEG

4

1

61.4

61.2

61.4

63.6

65.2

image passage

336x336 JPEG

4

2

114.4

114.5

116.2

118.5

35.1

image passage

336x336 JPEG

4

3

171.9

172.4

175.2

176.9

23.6

image passage

336x336 JPEG

4

5

283.4

288.2

293.0

294.7

14.7

image passage

336x336 JPEG

4

8

449.6

462.4

468.4

491.4

9.7

image passage

336x336 JPEG

8

1

120.8

120.3

121.0

124.0

66.2

image passage

336x336 JPEG

8

2

229.5

229.8

233.8

235.4

35.0

image passage

336x336 JPEG

8

3

343.5

345.4

349.5

351.6

23.6

image passage

336x336 JPEG

8

5

567.0

577.4

581.6

583.7

14.7

image passage

336x336 JPEG

8

8

896.8

924.4

931.6

962.6

9.8

image passage

512x512 JPEG

1

1

17.2

17.1

17.3

17.3

58.2

image passage

512x512 JPEG

1

2

28.2

28.2

28.3

28.3

35.5

image passage

512x512 JPEG

1

3

42.8

42.8

42.9

44.9

23.6

image passage

512x512 JPEG

1

5

70.6

71.8

71.9

74.7

14.6

image passage

512x512 JPEG

1

8

112.0

115.8

115.9

116.0

9.6

image passage

512x512 JPEG

4

1

62.6

62.1

62.5

66.6

64.0

image passage

512x512 JPEG

4

2

114.7

114.8

115.2

117.9

35.0

image passage

512x512 JPEG

4

3

171.3

172.7

173.2

174.0

23.6

image passage

512x512 JPEG

4

5

284.0

288.7

292.8

294.8

14.6

image passage

512x512 JPEG

4

8

447.5

462.7

464.2

468.5

9.8

image passage

512x512 JPEG

8

1

122.2

121.9

123.1

124.7

65.5

image passage

512x512 JPEG

8

2

229.8

230.1

233.8

234.9

35.0

image passage

512x512 JPEG

8

3

343.7

345.9

349.6

352.7

23.6

image passage

512x512 JPEG

8

5

568.2

578.1

582.0

585.9

14.6

image passage

512x512 JPEG

8

8

898.7

927.7

933.9

940.4

9.7

image passage

1024x1024 JPEG

1

1

63.8

63.7

64.2

64.3

15.7

image passage

1024x1024 JPEG

1

2

119.0

119.4

119.7

119.9

8.4

image passage

1024x1024 JPEG

1

3

178.1

179.6

180.2

180.6

5.7

image passage

1024x1024 JPEG

1

5

295.6

301.3

302.0

304.6

3.5

image passage

1024x1024 JPEG

1

8

483.0

481.1

496.3

687.1

2.3

image passage

1024x1024 JPEG

4

1

251.3

248.1

250.4

252.7

16.0

image passage

1024x1024 JPEG

4

2

483.4

479.6

482.4

484.3

8.3

image passage

1024x1024 JPEG

4

3

720.2

720.1

738.3

786.4

5.6

image passage

1024x1024 JPEG

4

5

1178.8

1201.5

1205.6

1206.6

3.5

image passage

1024x1024 JPEG

4

8

1861.6

1926.5

1937.7

1939.9

2.3

image passage

1024x1024 JPEG

8

1

494.1

493.7

495.4

498.2

16.2

image passage

1024x1024 JPEG

8

2

956.0

958.9

966.6

969.6

8.4

image passage

1024x1024 JPEG

8

3

1430.4

1442.1

1452.7

1457.8

5.7

image passage

1024x1024 JPEG

8

5

2359.9

2404.8

2414.0

2420.4

3.5

image passage

1024x1024 JPEG

8

8

3724.2

3854.9

3870.6

3872.7

2.4

image passage

2048x2048 JPEG

1

1

66.9

66.8

68.5

68.6

15.0

image passage

2048x2048 JPEG

1

2

119.7

120.3

120.5

120.6

8.4

image passage

2048x2048 JPEG

1

3

180.0

180.6

186.5

188.7

5.6

image passage

2048x2048 JPEG

1

5

296.4

302.0

303.9

304.2

3.5

image passage

2048x2048 JPEG

1

8

467.5

484.0

484.6

484.7

2.3

image passage

2048x2048 JPEG

4

1

257.8

256.9

259.5

261.4

15.5

image passage

2048x2048 JPEG

4

2

479.7

480.6

484.0

485.3

8.4

image passage

2048x2048 JPEG

4

3

718.2

723.3

730.0

732.6

5.6

image passage

2048x2048 JPEG

4

5

1197.2

1209.2

1230.5

1250.0

3.5

image passage

2048x2048 JPEG

4

8

1875.2

1939.4

1944.1

1972.7

2.3

image passage

2048x2048 JPEG

8

1

512.8

512.4

516.1

517.9

15.6

image passage

2048x2048 JPEG

8

2

976.2

965.6

995.9

1042.0

8.3

image passage

2048x2048 JPEG

8

3

1435.7

1448.2

1452.3

1457.4

5.6

image passage

2048x2048 JPEG

8

5

2388.4

2420.7

2455.6

2491.0

3.5

image passage

2048x2048 JPEG

8

8

3762.5

3883.6

3927.7

3985.5

2.3

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

10.0

10.0

10.1

10.1

92.6

query

20

1

3

18.5

18.5

18.7

18.7

153.4

query

20

1

5

19.9

19.7

19.8

22.0

236.8

query

20

1

7

28.6

29.5

29.7

29.7

227.6

query

20

1

9

22.1

22.6

23.3

23.5

367.8

query

20

1

11

23.2

23.3

24.2

24.4

433.7

query

20

1

13

31.4

33.1

33.6

33.7

379.4

query

20

1

15

32.8

34.2

34.7

35.1

406.8

passage

300

64

1

1104.3

1105.0

1114.6

1116.9

57.5

passage

300

64

3

3271.2

3303.0

3323.7

3332.1

58.0

passage

300

64

5

5406.1

5515.4

5546.1

5552.9

57.9

passage

512

64

1

2188.5

2186.1

2213.1

2221.7

29.1

passage

512

64

3

6509.7

6573.1

6608.2

6616.6

29.2

passage

512

64

5

10746.7

10966.7

11010.6

11025.5

29.2

image passage

336x336 JPEG

1

1

87.0

87.0

89.3

89.9

11.5

image passage

336x336 JPEG

1

2

169.2

169.9

172.6

173.3

5.9

image passage

336x336 JPEG

1

3

253.9

256.4

259.0

259.3

4.0

image passage

336x336 JPEG

1

5

419.6

428.1

431.5

432.1

2.5

image passage

336x336 JPEG

1

8

662.1

685.8

689.2

690.9

1.7

image passage

336x336 JPEG

4

1

346.3

346.2

349.7

350.5

11.6

image passage

336x336 JPEG

4

2

685.8

689.1

692.3

693.2

5.9

image passage

336x336 JPEG

4

3

1026.6

1037.2

1040.7

1041.5

4.0

image passage

336x336 JPEG

4

5

1696.5

1731.2

1735.5

1736.8

2.5

image passage

336x336 JPEG

4

8

2674.5

2771.0

2776.2

2777.0

1.6

image passage

336x336 JPEG

8

1

696.4

696.0

699.9

701.0

11.5

image passage

336x336 JPEG

8

2

1378.7

1385.2

1390.5

1391.7

5.8

image passage

336x336 JPEG

8

3

2060.2

2080.3

2086.4

2088.0

3.9

image passage

336x336 JPEG

8

5

3400.5

3469.7

3477.2

3478.7

2.5

image passage

336x336 JPEG

8

8

5358.8

5552.8

5560.9

5563.9

1.6

image passage

512x512 JPEG

1

1

87.8

87.9

89.5

89.8

11.4

image passage

512x512 JPEG

1

2

170.4

171.3

173.8

174.4

5.9

image passage

512x512 JPEG

1

3

254.5

256.9

259.7

260.3

4.0

image passage

512x512 JPEG

1

5

421.5

429.7

432.5

434.1

2.5

image passage

512x512 JPEG

1

8

663.6

687.3

690.3

691.5

1.7

image passage

512x512 JPEG

4

1

347.5

347.1

350.8

351.6

11.5

image passage

512x512 JPEG

4

2

685.9

689.4

692.6

693.4

5.9

image passage

512x512 JPEG

4

3

1027.0

1037.1

1041.0

1042.9

4.0

image passage

512x512 JPEG

4

5

1694.8

1729.1

1733.5

1734.7

2.5

image passage

512x512 JPEG

4

8

2672.8

2769.4

2773.3

2778.1

1.6

image passage

512x512 JPEG

8

1

696.5

696.7

699.6

701.1

11.5

image passage

512x512 JPEG

8

2

1379.2

1386.1

1391.2

1391.6

5.8

image passage

512x512 JPEG

8

3

2058.7

2079.3

2083.8

2086.6

3.9

image passage

512x512 JPEG

8

5

3399.9

3468.4

3476.6

3480.0

2.5

image passage

512x512 JPEG

8

8

5357.3

5550.7

5561.2

5566.0

1.6

image passage

1024x1024 JPEG

1

1

465.9

462.6

476.9

480.6

2.1

image passage

1024x1024 JPEG

1

2

921.7

920.3

946.6

951.2

1.1

image passage

1024x1024 JPEG

1

3

1378.9

1390.7

1412.4

1431.6

0.7

image passage

1024x1024 JPEG

1

5

2267.7

2313.3

2328.9

2332.3

0.5

image passage

1024x1024 JPEG

1

8

3580.6

3704.8

3734.6

3748.2

0.3

image passage

1024x1024 JPEG

4

1

1864.2

1864.9

1877.4

1882.0

2.1

image passage

1024x1024 JPEG

4

2

3695.1

3708.9

3735.8

3746.2

1.1

image passage

1024x1024 JPEG

4

3

5509.4

5566.5

5583.7

5585.1

0.7

image passage

1024x1024 JPEG

4

5

9098.7

9280.1

9306.9

9323.1

0.5

image passage

1024x1024 JPEG

4

8

14327.0

14843.6

14886.3

14897.9

0.3

image passage

1024x1024 JPEG

8

1

3726.8

3723.1

3748.4

3757.9

2.1

image passage

1024x1024 JPEG

8

2

7395.5

7428.5

7459.6

7483.6

1.1

image passage

1024x1024 JPEG

8

3

11044.6

11154.7

11192.7

11200.7

0.7

image passage

1024x1024 JPEG

8

5

18205.8

18577.5

18614.3

18618.1

0.5

image passage

1024x1024 JPEG

8

8

28702.8

29714.8

29850.5

29966.5

0.3

image passage

2048x2048 JPEG

1

1

468.4

464.4

481.6

483.0

2.1

image passage

2048x2048 JPEG

1

2

920.0

920.0

941.3

946.8

1.1

image passage

2048x2048 JPEG

1

3

1373.0

1384.2

1407.0

1409.6

0.7

image passage

2048x2048 JPEG

1

5

2268.4

2313.8

2326.4

2327.6

0.5

image passage

2048x2048 JPEG

1

8

3576.4

3703.5

3732.0

3740.5

0.3

image passage

2048x2048 JPEG

4

1

1863.3

1862.4

1879.9

1883.3

2.1

image passage

2048x2048 JPEG

4

2

3695.4

3711.7

3735.0

3739.0

1.1

image passage

2048x2048 JPEG

4

3

5510.1

5567.9

5582.6

5586.7

0.7

image passage

2048x2048 JPEG

4

5

9087.8

9270.3

9300.1

9312.2

0.5

image passage

2048x2048 JPEG

4

8

14332.3

14851.5

14876.4

14885.6

0.3

image passage

2048x2048 JPEG

8

1

3731.9

3729.7

3751.4

3759.3

2.1

image passage

2048x2048 JPEG

8

2

7393.5

7427.6

7460.4

7477.7

1.1

image passage

2048x2048 JPEG

8

3

11035.5

11149.6

11177.5

11183.9

0.7

image passage

2048x2048 JPEG

8

5

18226.0

18573.6

18637.3

18684.3

0.5

image passage

2048x2048 JPEG

8

8

28696.2

29727.8

29790.0

29803.4

0.3

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

4.2

4.2

4.2

4.2

207.2

query

20

1

3

6.6

6.9

7.0

7.0

403.9

query

20

1

5

7.1

7.1

7.3

7.3

624.6

query

20

1

7

7.3

7.3

7.5

7.5

843.0

query

20

1

9

10.8

11.2

11.3

11.4

729.9

query

20

1

11

7.9

8.0

8.2

9.2

1186.2

query

20

1

13

8.2

8.3

8.6

9.7

1347.5

query

20

1

15

8.4

8.4

10.0

10.1

1502.9

passage

300

64

1

336.2

336.3

337.5

337.8

185.7

passage

300

64

3

977.5

987.6

989.9

990.3

192.8

passage

300

64

5

1618.4

1652.1

1654.9

1655.9

192.8

passage

512

64

1

647.5

648.6

652.7

657.9

97.6

passage

512

64

3

1938.7

1958.4

1974.7

1979.3

97.6

passage

512

64

5

3233.8

3301.3

3313.4

3316.3

96.7

image passage

336x336 JPEG

1

1

28.9

28.5

30.2

32.3

34.6

image passage

336x336 JPEG

1

2

52.5

51.9

55.1

58.0

19.1

image passage

336x336 JPEG

1

3

78.9

78.4

84.4

86.2

12.8

image passage

336x336 JPEG

1

5

130.6

131.1

139.0

140.0

8.0

image passage

336x336 JPEG

1

8

206.4

210.2

219.1

219.7

5.3

image passage

336x336 JPEG

4

1

110.4

108.8

116.3

117.4

36.3

image passage

336x336 JPEG

4

2

212.9

211.4

219.8

220.6

18.9

image passage

336x336 JPEG

4

3

319.1

323.5

326.8

327.3

12.7

image passage

336x336 JPEG

4

5

527.5

537.9

540.4

540.9

7.9

image passage

336x336 JPEG

4

8

833.2

862.1

868.9

869.3

5.3

image passage

336x336 JPEG

8

1

220.3

218.4

225.7

226.4

36.3

image passage

336x336 JPEG

8

2

430.3

433.2

435.7

436.4

18.7

image passage

336x336 JPEG

8

3

643.7

649.7

656.6

658.0

12.6

image passage

336x336 JPEG

8

5

1064.9

1086.6

1089.3

1091.0

7.8

image passage

336x336 JPEG

8

8

1683.4

1742.4

1750.7

1751.6

5.2

image passage

512x512 JPEG

1

1

29.4

29.0

30.4

32.4

34.1

image passage

512x512 JPEG

1

2

53.1

52.5

55.6

59.0

18.9

image passage

512x512 JPEG

1

3

79.6

79.1

85.2

87.2

12.7

image passage

512x512 JPEG

1

5

131.7

132.2

140.7

142.6

7.9

image passage

512x512 JPEG

1

8

207.7

211.8

221.5

221.9

5.3

image passage

512x512 JPEG

4

1

111.5

109.9

117.5

118.4

35.9

image passage

512x512 JPEG

4

2

213.8

212.4

220.7

221.4

18.8

image passage

512x512 JPEG

4

3

319.8

323.6

327.6

328.0

12.7

image passage

512x512 JPEG

4

5

529.1

539.6

543.6

544.4

7.9

image passage

512x512 JPEG

4

8

835.2

864.7

870.5

872.0

5.2

image passage

512x512 JPEG

8

1

221.7

219.7

227.6

227.9

36.1

image passage

512x512 JPEG

8

2

429.9

432.7

435.5

436.2

18.7

image passage

512x512 JPEG

8

3

644.6

649.8

657.1

659.3

12.6

image passage

512x512 JPEG

8

5

1066.3

1088.1

1092.0

1093.3

7.8

image passage

512x512 JPEG

8

8

1679.4

1739.0

1747.9

1749.4

5.2

image passage

1024x1024 JPEG

1

1

149.5

147.3

157.5

158.5

6.7

image passage

1024x1024 JPEG

1

2

288.9

287.1

300.6

301.9

3.5

image passage

1024x1024 JPEG

1

3

432.0

431.3

448.2

451.8

2.3

image passage

1024x1024 JPEG

1

5

713.0

725.5

737.6

742.5

1.5

image passage

1024x1024 JPEG

1

8

1122.4

1164.3

1171.6

1171.8

1.0

image passage

1024x1024 JPEG

4

1

590.6

584.6

604.3

605.9

6.8

image passage

1024x1024 JPEG

4

2

1165.0

1172.2

1181.3

1182.8

3.4

image passage

1024x1024 JPEG

4

3

1739.6

1756.2

1768.0

1771.9

2.3

image passage

1024x1024 JPEG

4

5

2870.5

2929.2

2938.8

2946.4

1.5

image passage

1024x1024 JPEG

4

8

4524.7

4687.8

4701.4

4702.9

1.0

image passage

1024x1024 JPEG

8

1

1185.2

1186.0

1194.4

1196.2

6.8

image passage

1024x1024 JPEG

8

2

2335.2

2348.2

2359.3

2361.2

3.4

image passage

1024x1024 JPEG

8

3

3478.4

3511.3

3529.7

3533.6

2.3

image passage

1024x1024 JPEG

8

5

5755.0

5872.1

5887.7

5897.0

1.4

image passage

1024x1024 JPEG

8

8

9119.4

9396.7

9429.2

10020.8

1.0

image passage

2048x2048 JPEG

1

1

151.1

150.1

159.2

161.0

6.6

image passage

2048x2048 JPEG

1

2

289.5

287.5

301.9

306.0

3.5

image passage

2048x2048 JPEG

1

3

431.6

431.6

445.9

449.0

2.4

image passage

2048x2048 JPEG

1

5

712.0

725.5

739.4

740.7

1.5

image passage

2048x2048 JPEG

1

8

1123.8

1163.0

1173.5

1174.9

1.0

image passage

2048x2048 JPEG

4

1

597.8

596.1

611.9

613.6

6.7

image passage

2048x2048 JPEG

4

2

1159.1

1166.7

1174.1

1175.9

3.5

image passage

2048x2048 JPEG

4

3

1732.7

1749.6

1762.3

1766.1

2.3

image passage

2048x2048 JPEG

4

5

2861.1

2915.5

2935.8

2939.2

1.5

image passage

2048x2048 JPEG

4

8

4507.9

4671.0

4692.5

4694.9

1.0

image passage

2048x2048 JPEG

8

1

1197.7

1198.8

1208.7

1211.2

6.7

image passage

2048x2048 JPEG

8

2

2320.4

2332.1

2350.3

2354.3

3.5

image passage

2048x2048 JPEG

8

3

3467.4

3501.4

3525.5

3530.1

2.3

image passage

2048x2048 JPEG

8

5

5734.6

5854.6

5876.2

5879.3

1.5

image passage

2048x2048 JPEG

8

8

9030.5

9361.0

9400.7

9411.1

1.0

Input Type

Input Tokens

Image Size

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

6.3

6.2

6.3

6.3

143.7

query

20

1

3

10.4

11.0

11.2

11.2

263.4

query

20

1

5

11.7

11.8

12.0

12.0

384.0

query

20

1

7

12.9

13.0

13.2

13.3

488.6

query

20

1

9

14.4

14.5

14.9

16.0

559.7

query

20

1

11

20.9

21.3

21.6

22.7

478.1

query

20

1

13

20.9

21.2

22.9

23.1

556.9

query

20

1

15

21.1

21.4

25.6

25.7

635.1

passage

300

64

1

1171.3

1171.2

1178.0

1180.2

54.3

passage

300

64

3

3463.7

3498.8

3507.1

3508.2

54.8

passage

300

64

5

5720.4

5839.0

5849.4

5855.6

54.7

passage

512

64

1

2137.1

2140.7

2180.9

2208.9

29.8

passage

512

64

3

6409.9

6474.2

6517.6

6531.5

29.6

passage

512

64

5

10634.0

10818.2

10997.6

11028.1

29.5

image passage

336x336 JPEG

1

1

77.0

77.0

79.0

80.1

13.0

image passage

336x336 JPEG

1

2

151.4

151.7

156.1

157.6

6.6

image passage

336x336 JPEG

1

3

228.3

230.0

237.5

239.1

4.4

image passage

336x336 JPEG

1

5

376.9

386.0

388.8

389.7

2.8

image passage

336x336 JPEG

1

8

595.3

618.2

629.1

630.1

1.8

image passage

336x336 JPEG

4

1

318.2

317.4

326.1

326.7

12.6

image passage

336x336 JPEG

4

2

631.7

635.6

643.5

648.3

6.4

image passage

336x336 JPEG

4

3

948.5

955.9

973.0

975.1

4.3

image passage

336x336 JPEG

4

5

1565.0

1595.8

1607.9

1615.5

2.7

image passage

336x336 JPEG

4

8

2472.0

2555.7

2582.2

2597.4

1.8

image passage

336x336 JPEG

8

1

645.4

645.9

650.6

653.4

12.4

image passage

336x336 JPEG

8

2

1278.3

1285.2

1294.7

1299.9

6.3

image passage

336x336 JPEG

8

3

1911.8

1931.6

1945.2

1947.8

4.2

image passage

336x336 JPEG

8

5

3154.5

3216.9

3238.7

3247.3

2.6

image passage

336x336 JPEG

8

8

4966.3

5147.1

5178.2

5184.0

1.8

image passage

512x512 JPEG

1

1

81.5

80.2

85.9

91.9

12.3

image passage

512x512 JPEG

1

2

155.5

155.7

160.8

162.6

6.5

image passage

512x512 JPEG

1

3

232.0

233.8

239.1

240.8

4.4

image passage

512x512 JPEG

1

5

384.1

390.8

399.5

401.3

2.7

image passage

512x512 JPEG

1

8

601.9

623.0

638.8

640.3

1.8

image passage

512x512 JPEG

4

1

319.9

319.2

327.5

329.1

12.5

image passage

512x512 JPEG

4

2

633.1

636.7

640.9

643.6

6.4

image passage

512x512 JPEG

4

3

947.7

957.4

966.6

969.1

4.3

image passage

512x512 JPEG

4

5

1565.0

1596.5

1611.9

1614.5

2.7

image passage

512x512 JPEG

4

8

2466.5

2556.6

2575.5

2578.4

1.8

image passage

512x512 JPEG

8

1

645.4

645.1

654.4

656.8

12.4

image passage

512x512 JPEG

8

2

1278.3

1283.7

1298.9

1301.8

6.3

image passage

512x512 JPEG

8

3

1907.1

1928.4

1943.2

1947.5

4.3

image passage

512x512 JPEG

8

5

3149.6

3214.2

3238.3

3242.0

2.7

image passage

512x512 JPEG

8

8

4970.0

5153.5

5174.4

5180.6

1.8

image passage

1024x1024 JPEG

1

1

418.3

416.6

428.1

433.1

2.4

image passage

1024x1024 JPEG

1

2

824.2

826.9

839.9

846.3

1.2

image passage

1024x1024 JPEG

1

3

1232.5

1241.7

1261.7

1266.2

0.8

image passage

1024x1024 JPEG

1

5

2031.5

2071.0

2092.5

2102.3

0.5

image passage

1024x1024 JPEG

1

8

3200.8

3317.1

3341.4

3346.4

0.3

image passage

1024x1024 JPEG

4

1

1673.2

1672.9

1687.6

1691.2

2.4

image passage

1024x1024 JPEG

4

2

3326.9

3339.5

3356.2

3364.5

1.2

image passage

1024x1024 JPEG

4

3

4954.8

5004.8

5027.8

5031.4

0.8

image passage

1024x1024 JPEG

4

5

8175.0

8343.3

8364.3

8368.3

0.5

image passage

1024x1024 JPEG

4

8

12880.9

13353.1

13379.7

13387.6

0.3

image passage

1024x1024 JPEG

8

1

3349.5

3350.6

3366.1

3369.4

2.4

image passage

1024x1024 JPEG

8

2

6645.6

6679.9

6702.3

6706.0

1.2

image passage

1024x1024 JPEG

8

3

9926.7

10025.7

10060.1

10066.6

0.8

image passage

1024x1024 JPEG

8

5

16384.2

16720.9

16761.6

16774.9

0.5

image passage

1024x1024 JPEG

8

8

25793.0

26726.9

26766.8

26785.6

0.3

image passage

2048x2048 JPEG

1

1

418.1

416.2

427.3

434.6

2.4

image passage

2048x2048 JPEG

1

2

821.4

822.1

841.6

848.2

1.2

image passage

2048x2048 JPEG

1

3

1225.7

1236.4

1256.1

1260.2

0.8

image passage

2048x2048 JPEG

1

5

2023.9

2064.9

2088.0

2091.2

0.5

image passage

2048x2048 JPEG

1

8

3185.8

3304.6

3329.7

3336.3

0.3

image passage

2048x2048 JPEG

4

1

1675.1

1676.4

1696.7

1702.0

2.4

image passage

2048x2048 JPEG

4

2

3312.6

3332.9

3352.7

3357.7

1.2

image passage

2048x2048 JPEG

4

3

4949.6

5001.9

5028.8

5037.4

0.8

image passage

2048x2048 JPEG

4

5

8157.4

8330.8

8358.3

8368.9

0.5

image passage

2048x2048 JPEG

4

8

12861.0

13340.3

13401.5

13411.9

0.3

image passage

2048x2048 JPEG

8

1

3359.5

3360.5

3379.8

3385.4

2.4

image passage

2048x2048 JPEG

8

2

6645.9

6681.6

6705.8

6710.8

1.2

image passage

2048x2048 JPEG

8

3

9929.8

10031.0

10060.4

10068.0

0.8

image passage

2048x2048 JPEG

8

5

16388.4

16735.1

16765.1

16774.6

0.5

image passage

2048x2048 JPEG

8

8

25765.3

26693.5

26773.7

26778.5

0.3

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

7.8

8.0

8.0

8.3

126.0

passage

20

1

3

8.3

8.0

9.0

8.8

348.0

passage

20

1

5

8.8

8.0

9.0

10.3

547.0

passage

20

1

7

10.8

11.0

12.0

11.9

585.0

passage

20

1

9

13.2

13.0

15.0

15.1

643.0

passage

20

1

11

15.5

16.0

18.0

18.4

652.0

passage

20

1

13

17.5

17.0

21.0

21.5

673.0

passage

20

1

15

20.6

21.0

24.0

24.0

662.0

passage

300

64

1

69.5

69.0

71.0

72.3

896.0

passage

300

64

3

103.5

104.0

107.0

108.3

1779.0

passage

300

64

5

172.3

173.0

178.0

179.9

1799.0

passage

512

64

1

103.6

101.0

116.0

120.1

606.0

passage

512

64

3

180.6

182.0

192.0

193.6

1040.0

passage

512

64

5

298.6

300.0

318.0

325.1

1041.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.0

8.0

9.0

8.9

122.0

passage

20

1

3

8.6

8.0

9.0

9.2

340.0

passage

20

1

5

8.8

9.0

9.0

9.2

548.0

passage

20

1

7

10.9

11.0

12.0

12.6

575.0

passage

20

1

9

13.3

14.0

15.0

15.2

638.0

passage

20

1

11

15.4

16.0

17.0

17.9

668.0

passage

20

1

13

17.6

17.0

21.0

21.3

688.0

passage

20

1

15

21.2

22.0

24.0

24.9

645.0

passage

300

64

1

70.9

71.0

73.0

74.3

880.0

passage

300

64

3

112.8

113.0

117.0

118.4

1652.0

passage

300

64

5

187.7

189.0

194.0

194.9

1653.0

passage

512

64

1

109.5

108.0

128.0

128.9

574.0

passage

512

64

3

202.5

203.0

216.0

219.4

919.0

passage

512

64

5

336.4

338.0

352.0

356.9

926.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.2

8.0

9.0

8.6

120.0

passage

20

1

3

8.5

8.0

9.0

9.2

345.0

passage

20

1

5

9.4

9.0

10.0

10.8

508.0

passage

20

1

7

11.4

11.0

13.0

13.4

576.0

passage

20

1

9

14.4

15.0

17.0

16.9

584.0

passage

20

1

11

16.6

16.0

20.0

20.2

602.0

passage

20

1

13

20.2

21.0

24.0

24.2

590.0

passage

20

1

15

22.6

23.0

26.0

26.7

600.0

passage

300

64

1

68.8

68.0

72.0

73.1

907.0

passage

300

64

3

119.3

120.0

125.0

126.4

1552.0

passage

300

64

5

199.8

202.0

208.0

210.3

1555.0

passage

512

64

1

112.7

112.0

125.0

131.9

559.0

passage

512

64

3

229.5

232.0

242.0

246.6

814.0

passage

512

64

5

383.5

391.0

401.0

407.0

813.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.2

8.0

8.0

8.7

120.0

passage

20

1

3

8.3

8.0

9.0

8.8

339.0

passage

20

1

5

8.7

9.0

9.0

9.3

535.0

passage

20

1

7

10.7

11.0

12.0

11.8

597.0

passage

20

1

9

13.2

13.0

15.0

15.2

642.0

passage

20

1

11

15.5

16.0

18.0

18.3

654.0

passage

20

1

13

18.4

19.0

21.0

21.4

650.0

passage

20

1

15

20.8

21.0

24.0

24.5

668.0

passage

300

64

1

78.7

79.0

82.0

82.8

795.0

passage

300

64

3

149.7

151.0

156.0

157.8

1250.0

passage

300

64

5

249.8

254.0

260.0

261.9

1246.0

passage

512

64

1

129.6

127.0

142.0

150.2

487.0

passage

512

64

3

283.1

286.0

299.0

302.8

660.0

passage

512

64

5

474.0

482.0

499.0

502.4

658.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.3

8.0

8.0

8.7

118.0

passage

20

1

3

9.0

9.0

9.0

9.5

320.0

passage

20

1

5

9.9

10.0

11.0

11.4

476.0

passage

20

1

7

11.5

12.0

14.0

13.7

573.0

passage

20

1

9

14.4

14.0

16.0

16.5

583.0

passage

20

1

11

17.8

18.0

21.0

21.7

518.0

passage

20

1

13

20.2

20.0

24.0

23.7

582.0

passage

20

1

15

20.5

21.0

24.0

24.7

664.0

passage

300

64

1

97.3

97.0

99.0

100.2

646.0

passage

300

64

3

200.0

202.0

204.0

204.9

940.0

passage

300

64

5

332.7

336.0

340.0

340.5

938.0

passage

512

64

1

199.9

189.0

261.0

268.1

317.0

passage

512

64

3

415.9

419.0

427.0

428.2

455.0

passage

512

64

5

690.1

701.0

711.0

712.8

453.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.6

9.0

9.0

9.1

114.0

passage

20

1

3

9.3

9.0

10.0

10.2

312.0

passage

20

1

5

10.5

10.0

11.0

11.2

459.0

passage

20

1

7

14.4

14.0

15.0

21.8

453.0

passage

20

1

9

17.6

18.0

20.0

20.2

476.0

passage

20

1

11

20.2

21.0

25.0

24.9

499.0

passage

20

1

13

24.5

24.0

27.0

28.4

480.0

passage

20

1

15

28.7

30.0

33.0

33.3

471.0

passage

300

64

1

124.1

124.0

126.0

127.2

508.0

passage

300

64

3

273.1

275.0

278.0

279.2

692.0

passage

300

64

5

451.2

458.0

463.0

463.7

692.0

passage

512

64

1

239.6

230.0

297.0

301.0

265.0

passage

512

64

3

529.9

534.0

541.0

542.7

357.0

passage

512

64

5

876.4

892.0

900.0

901.8

357.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

5.5

5.0

7.0

7.0

180.0

passage

20

1

3

7.0

7.0

7.0

7.1

421.0

passage

20

1

5

10.5

11.0

12.0

11.8

455.0

passage

20

1

7

12.6

12.0

16.0

16.4

529.0

passage

20

1

9

18.5

20.0

21.0

21.3

466.0

passage

20

1

11

19.6

19.0

23.0

25.2

524.0

passage

20

1

13

24.6

25.0

28.0

30.1

481.0

passage

20

1

15

26.4

28.0

30.0

30.3

509.0

passage

300

64

1

115.7

115.0

120.0

120.4

544.0

passage

300

64

3

229.7

231.0

236.0

239.2

817.0

passage

300

64

5

381.6

385.0

393.0

397.6

817.0

passage

512

64

1

199.6

195.0

237.0

242.4

317.0

passage

512

64

3

431.6

433.0

447.0

448.9

438.0

passage

512

64

5

715.0

724.0

740.0

746.6

437.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

9.6

9.0

10.0

11.0

103.0

passage

20

1

3

12.6

13.0

14.0

14.2

232.0

passage

20

1

5

20.6

22.0

23.0

23.1

237.0

passage

20

1

7

28.3

31.0

32.0

31.7

234.0

passage

20

1

9

35.1

36.0

41.0

41.8

244.0

passage

20

1

11

43.3

45.0

50.0

50.4

236.0

passage

20

1

13

52.6

54.0

59.0

58.8

234.0

passage

20

1

15

58.0

60.0

68.0

68.7

234.0

passage

300

64

1

304.9

305.0

309.0

310.3

209.0

passage

300

64

3

780.6

791.0

799.0

800.0

241.0

passage

300

64

5

1296.8

1320.0

1330.0

1331.8

241.0

passage

512

64

1

520.7

519.0

533.0

538.6

122.0

passage

512

64

3

1385.5

1404.0

1424.0

1428.4

137.0

passage

512

64

5

2294.3

2341.0

2362.0

2368.3

137.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

20

1

1

8.8

8.0

10.0

10.0

113.0

passage

20

1

3

11.1

11.0

12.0

11.8

259.0

passage

20

1

5

16.4

16.0

19.0

18.9

295.0

passage

20

1

7

23.3

22.0

26.0

26.8

290.0

passage

20

1

9

29.5

30.0

33.0

33.9

289.0

passage

20

1

11

34.2

34.0

40.0

40.6

302.0

passage

20

1

13

41.6

44.0

47.0

48.1

288.0

passage

20

1

15

45.7

48.0

55.0

55.2

300.0

passage

300

64

1

339.6

339.0

343.0

345.5

187.0

passage

300

64

3

918.3

927.0

933.0

934.6

207.0

passage

300

64

5

1517.3

1547.0

1554.0

1555.5

206.0

passage

512

64

1

642.3

643.0

657.0

661.9

99.0

passage

512

64

3

1795.3

1818.0

1835.0

1841.2

105.0

passage

512

64

5

2976.6

3034.0

3066.0

3075.5

105.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

7.0

7.0

8.0

8.0

140.7

query

20

1

3

10.0

10.0

10.0

10.0

291.7

query

20

1

5

16.0

17.0

17.0

17.0

307.0

query

20

1

7

22.0

23.0

24.0

24.0

310.9

query

20

1

9

25.0

26.0

31.0

31.0

329.7

query

20

1

11

30.0

32.0

38.0

38.0

332.8

query

20

1

13

36.0

37.0

43.0

44.0

340.0

query

20

1

15

42.0

43.0

48.0

50.0

327.5

passage

300

64

1

159.0

159.0

162.0

163.0

401.8

passage

300

64

3

267.0

269.0

275.0

277.0

709.4

passage

300

64

5

392.0

390.0

401.0

411.0

814.5

passage

512

64

1

222.0

218.0

233.0

235.0

286.3

passage

512

64

3

431.0

430.0

450.0

455.0

440.1

passage

512

64

5

615.0

617.0

694.0

701.0

504.3

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

8.0

8.0

8.0

9.0

125.6

query

20

1

3

12.0

12.0

13.0

13.0

246.1

query

20

1

5

20.0

21.0

22.0

22.0

247.9

query

20

1

7

25.0

26.0

30.0

30.0

267.5

query

20

1

9

34.0

34.0

38.0

39.0

251.5

query

20

1

11

43.0

46.0

47.0

48.0

237.7

query

20

1

13

46.0

49.0

53.0

54.0

260.9

query

20

1

15

55.0

58.0

65.0

65.0

248.4

passage

300

64

1

186.0

186.0

190.0

192.0

342.7

passage

300

64

3

345.0

346.0

354.0

356.0

550.7

passage

300

64

5

525.0

524.0

535.0

544.0

608.3

passage

512

64

1

269.0

265.0

280.0

284.0

237.2

passage

512

64

3

563.0

564.0

581.0

584.0

337.3

passage

512

64

5

846.0

861.0

946.0

956.0

366.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

10.0

10.0

10.0

11.0

98.0

query

20

1

3

15.0

17.0

17.0

17.0

192.5

query

20

1

5

24.0

23.0

28.0

28.0

200.8

query

20

1

7

34.0

34.0

39.0

40.0

197.0

query

20

1

9

44.0

45.0

51.0

51.0

197.3

query

20

1

11

53.0

56.0

62.0

62.0

196.8

query

20

1

13

63.0

67.0

73.0

73.0

190.6

query

20

1

15

73.0

79.0

84.0

84.0

188.3

passage

300

64

1

277.0

278.0

280.0

281.0

230.3

passage

300

64

3

615.0

617.0

629.0

632.0

309.4

passage

300

64

5

976.0

975.0

983.0

987.0

327.4

passage

512

64

1

443.0

441.0

448.0

454.0

144.3

passage

512

64

3

1071.0

1077.0

1089.0

1090.0

177.6

passage

512

64

5

1736.0

1735.0

1752.0

1758.0

184.1

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

12.0

12.0

12.0

12.0

85.7

query

20

1

3

19.0

21.0

22.0

22.0

150.3

query

20

1

5

32.0

29.0

36.0

36.0

152.8

query

20

1

7

46.0

50.0

50.0

50.0

148.0

query

20

1

9

55.0

57.0

65.0

65.0

156.3

query

20

1

11

68.0

72.0

79.0

79.0

154.5

query

20

1

13

79.0

86.0

93.0

93.0

154.4

query

20

1

15

84.0

86.0

95.0

101.0

165.0

passage

300

64

1

350.0

350.0

353.0

354.0

182.8

passage

300

64

3

821.0

823.0

831.0

842.0

231.7

passage

300

64

5

1320.0

1317.0

1330.0

1346.0

242.1

passage

512

64

1

567.0

566.0

573.0

575.0

112.7

passage

512

64

3

1440.0

1448.0

1464.0

1475.0

132.2

passage

512

64

5

2370.0

2371.0

2391.0

2396.0

134.8

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

8.0

8.0

9.0

10.0

122.3

query

20

1

3

11.0

12.0

14.0

14.0

252.9

query

20

1

5

20.0

19.0

23.0

24.0

250.9

query

20

1

7

27.0

27.0

31.0

32.0

251.6

query

20

1

9

30.0

30.0

37.0

42.0

280.1

query

20

1

11

41.0

42.0

47.0

51.0

250.9

query

20

1

13

46.0

49.0

53.0

57.0

262.0

query

20

1

15

50.0

51.0

60.0

63.0

269.7

passage

300

64

1

325.0

324.0

331.0

333.0

196.9

passage

300

64

3

699.0

699.0

717.0

723.0

272.1

passage

300

64

5

1095.0

1093.0

1109.0

1113.0

291.8

passage

512

64

1

496.0

497.0

502.0

518.0

128.8

passage

512

64

3

1165.0

1169.0

1199.0

1209.0

163.2

passage

512

64

5

1872.0

1870.0

1904.0

1916.0

170.5

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

10.0

9.0

10.0

10.0

104.7

query

20

1

3

12.0

12.0

12.0

12.0

246.7

query

20

1

5

18.0

19.0

20.0

20.0

276.7

query

20

1

7

25.0

24.0

28.0

28.0

268.9

query

20

1

9

30.0

31.0

36.0

36.0

291.4

query

20

1

11

38.0

39.0

44.0

44.0

270.3

query

20

1

13

43.0

44.0

52.0

52.0

272.4

query

20

1

15

49.0

52.0

56.0

57.0

276.4

passage

300

64

1

362.0

362.0

367.0

369.0

176.8

passage

300

64

3

786.0

789.0

803.0

812.0

241.9

passage

300

64

5

1240.0

1239.0

1258.0

1262.0

257.6

passage

512

64

1

550.0

548.0

565.0

570.0

116.2

passage

512

64

3

1327.0

1335.0

1354.0

1359.0

143.4

passage

512

64

5

2145.0

2145.0

2180.0

2187.0

149.0

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

21.0

21.0

21.0

21.0

48.6

query

20

1

3

39.0

44.0

45.0

45.0

75.8

query

20

1

5

61.0

60.0

75.0

75.0

80.2

query

20

1

7

85.0

89.0

104.0

105.0

79.2

query

20

1

9

109.0

119.0

134.0

134.0

79.0

query

20

1

11

144.0

149.0

164.0

164.0

73.2

query

20

1

13

159.0

164.0

194.0

194.0

76.5

query

20

1

15

175.0

179.0

209.0

209.0

79.4

passage

300

64

1

888.0

888.0

899.0

899.0

72.1

passage

300

64

3

2272.0

2280.0

2329.0

2341.0

83.9

passage

300

64

5

3795.0

3801.0

3828.0

3840.0

84.2

passage

512

64

1

1451.0

1451.0

1471.0

1473.0

44.1

passage

512

64

3

3926.0

3947.0

3988.0

4009.0

48.6

passage

512

64

5

6577.0

6571.0

6632.0

6657.0

48.6

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

13.0

13.0

14.0

15.0

74.2

query

20

1

3

21.0

23.0

23.0

23.0

138.0

query

20

1

5

32.0

31.0

39.0

39.0

152.2

query

20

1

7

46.0

46.0

53.0

54.0

145.8

query

20

1

9

56.0

61.0

69.0

69.0

150.3

query

20

1

11

67.0

69.0

76.0

77.0

154.0

query

20

1

13

86.0

91.0

98.0

99.0

141.2

query

20

1

15

98.0

105.0

113.0

114.0

141.0

passage

300

64

1

724.0

725.0

730.0

733.0

88.3

passage

300

64

3

1865.0

1876.0

1891.0

1892.0

102.1

passage

300

64

5

3117.0

3127.0

3147.0

3150.0

102.1

passage

512

64

1

1300.0

1300.0

1314.0

1318.0

49.2

passage

512

64

3

3551.0

3577.0

3606.0

3618.0

53.6

passage

512

64

5

5940.0

5968.0

6000.0

6007.0

53.6

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

query

20

1

1

18.0

18.0

18.0

19.0

55.8

query

20

1

3

33.0

37.0

38.0

38.0

87.7

query

20

1

5

55.0

62.0

63.0

63.0

87.4

query

20

1

7

71.0

75.0

88.0

88.0

94.6

query

20

1

9

96.0

101.0

114.0

114.0

90.3

query

20

1

11

115.0

126.0

139.0

139.0

89.8

query

20

1

13

131.0

138.0

164.0

164.0

91.4

query

20

1

15

154.0

157.0

189.0

189.0

88.4

passage

300

64

1

1011.0

1011.0

1019.0

1019.0

63.3

passage

300

64

3

2702.0

2716.0

2734.0

2754.0

70.6

passage

300

64

5

4527.0

4527.0

4550.0

4571.0

70.6

passage

512

64

1

1705.0

1710.0

1733.0

1740.0

37.5

passage

512

64

3

4770.0

4799.0

4860.0

4872.0

39.9

passage

512

64

5

8001.0

8025.0

8079.0

8085.0

39.9

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

99.8

100.9

107.9

108.6

639.0

passage

300

64

3

143.8

143.3

156.6

159.0

1330.0

passage

300

64

5

239.7

239.7

259.1

265.0

1331.0

passage

512

64

1

114.6

114.4

115.9

117.0

556.5

passage

512

64

3

170.2

169.9

171.2

171.8

1124.2

passage

512

64

5

284.6

284.5

285.6

286.1

1121.4

query

20

1

1

5.1

5.1

5.4

5.4

196.3

query

20

1

3

6.0

5.5

7.4

7.6

498.5

query

20

1

5

11.9

12.3

12.8

12.9

418.3

query

20

1

7

16.5

17.2

18.0

18.1

422.0

query

20

1

9

21.4

22.3

23.3

23.6

418.3

query

20

1

11

26.0

26.0

28.4

28.6

421.3

query

20

1

13

30.7

30.9

33.1

33.6

422.2

query

20

1

15

37.3

37.9

39.1

39.3

401.4

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

2554.3

2563.9

2678.1

2698.3

25.0

passage

300

64

3

7349.2

7502.1

7889.3

7968.1

25.5

passage

300

64

5

11913.2

12461.9

12893.4

12969.4

25.6

passage

512

64

1

3701.9

3701.6

3703.1

3703.4

17.3

passage

512

64

3

10730.2

10985.2

10987.0

11029.2

17.5

passage

512

64

5

17355.4

14691.3

22035.4

22035.7

17.4

query

20

1

1

32.4

32.4

32.7

32.8

30.7

query

20

1

3

82.5

85.6

85.9

86.0

36.3

query

20

1

5

135.5

142.9

143.3

143.3

36.8

query

20

1

7

191.7

200.2

200.5

200.6

36.5

query

20

1

9

246.9

257.4

257.8

257.9

36.4

query

20

1

11

301.7

314.6

315.1

315.2

36.4

query

20

1

13

356.6

371.6

372.2

372.4

36.4

query

20

1

15

409.5

401.4

429.8

429.9

36.5

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

176.5

177.1

188.6

190.4

362.2

passage

300

64

3

336.1

337.0

359.1

365.8

570.2

passage

300

64

5

560.2

562.9

592.3

634.6

569.8

passage

512

64

1

205.3

204.7

208.2

210.8

311.4

passage

512

64

3

410.9

411.1

412.5

412.7

466.4

passage

512

64

5

681.5

682.0

683.6

684.1

468.7

query

20

1

1

5.3

5.3

5.6

5.7

186.3

query

20

1

3

7.4

7.4

7.5

7.7

403.8

query

20

1

5

11.9

12.4

12.6

12.8

419.2

query

20

1

7

16.6

17.3

17.5

17.6

421.5

query

20

1

9

21.2

22.1

22.5

22.6

423.9

query

20

1

11

26.1

27.2

27.7

27.8

420.5

query

20

1

13

30.8

31.2

32.6

32.7

422.3

query

20

1

15

36.4

37.3

37.9

38.0

411.7

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

188.4

191.7

197.7

198.8

338.7

passage

300

64

3

371.7

372.7

393.8

471.0

515.3

passage

300

64

5

619.5

621.7

648.5

728.8

515.1

passage

512

64

1

222.7

222.3

226.0

227.4

286.5

passage

512

64

3

447.0

447.0

448.7

449.4

428.4

passage

512

64

5

742.3

742.8

745.0

745.5

430.1

query

20

1

1

6.6

6.6

7.0

7.1

149.3

query

20

1

3

7.4

7.3

7.6

7.7

404.8

query

20

1

5

11.8

12.2

12.5

12.6

421.5

query

20

1

7

16.4

17.1

17.4

17.5

426.4

query

20

1

9

20.9

21.9

22.3

22.4

429.9

query

20

1

11

25.7

26.8

27.4

27.7

427.2

query

20

1

13

30.4

31.5

32.1

32.2

427.4

query

20

1

15

35.6

36.4

37.9

38.0

420.6

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

377.9

376.4

396.5

404.5

169.1

passage

300

64

3

929.9

932.3

972.0

979.2

205.8

passage

300

64

5

1545.5

1555.2

1597.3

1610.3

205.9

passage

512

64

1

469.5

468.6

473.9

475.1

136.2

passage

512

64

3

1178.9

1182.4

1183.0

1183.2

162.2

passage

512

64

5

1958.1

1970.9

1971.6

1971.8

162.2

query

20

1

1

11.1

11.1

11.5

11.6

89.8

query

20

1

3

19.3

20.3

20.8

21.0

154.9

query

20

1

5

32.1

34.0

34.6

34.8

155.5

query

20

1

7

44.8

47.4

48.1

48.2

156.0

query

20

1

9

57.7

60.9

61.8

62.0

155.8

query

20

1

11

70.6

74.0

75.5

75.7

155.5

query

20

1

13

83.8

82.8

89.2

89.6

154.9

query

20

1

15

97.5

96.6

103.1

103.4

153.7

Input Type

Input Tokens

Batch Size

Concurrency

Avg Latency

P50 Latency

P90 Latency

P95 Latency

Throughput (inputs/s)

passage

300

64

1

483.6

483.6

505.2

509.5

132.3

passage

300

64

3

1328.0

1334.4

1367.9

1379.6

143.9

passage

300

64

5

2181.8

2203.7

2241.9

2250.4

145.5

passage

512

64

1

633.8

633.8

638.6

639.4

100.9

passage

512

64

3

1744.9

1755.3

1761.5

1763.1

109.4

passage

512

64

5

2892.2

2923.9

2934.8

2936.8

109.4

query

20

1

1

8.0

8.0

8.3

8.3

124.1

query

20

1

3

11.2

12.2

12.6

12.8

266.1

query

20

1

5

19.9

20.6

21.1

21.2

250.3

query

20

1

7

27.6

28.9

29.4

29.6

253.0

query

20

1

9

35.1

36.7

37.3

37.5

256.1

query

20

1

11

42.7

44.6

45.5

45.7

256.9

query

20

1

13

50.7

50.3

54.0

54.2

255.9

query

20

1

15

57.4

57.9

62.2

62.5

261.0