nemo_export.tensorrt_llm_deployable_ray#

TensorRT-LLM Ray deployment functionality has been removed.

This module now only contains placeholder functions that raise NotImplementedError. TensorRT-LLM deployment support has been deprecated and removed from this codebase.

Module Contents#

Classes#

TensorRTLLMRayDeployable

Placeholder class for TensorRT-LLM Ray deployment functionality.

Data#

API#

nemo_export.tensorrt_llm_deployable_ray.LOGGER = 'getLogger(...)'#
class nemo_export.tensorrt_llm_deployable_ray.TensorRTLLMRayDeployable(
trt_llm_path: str,
model_id: str = 'tensorrt-llm-model',
use_python_runtime: bool = True,
enable_chunked_context: bool = None,
max_tokens_in_paged_kv_cache: int = None,
multi_block_mode: bool = False,
lora_ckpt_list: List[str] = None,
)[source]#

Placeholder class for TensorRT-LLM Ray deployment functionality.

Note: TensorRT-LLM deployment support has been removed from this codebase. All methods will raise NotImplementedError.

Initialization

Initialize the TensorRT-LLM model deployment.

Raises:

NotImplementedError – This functionality has been removed.

abstractmethod generate(*args, **kwargs)[source]#

Generate method.

Raises:

NotImplementedError – This functionality has been removed.

abstractmethod chat_completions(*args, **kwargs)[source]#

Chat completions method.

Raises:

NotImplementedError – This functionality has been removed.

abstractmethod completions(*args, **kwargs)[source]#

Completions method.

Raises:

NotImplementedError – This functionality has been removed.

abstractmethod classmethod options(*args, **kwargs)[source]#

Options method for Ray deployment.

Raises:

NotImplementedError – This functionality has been removed.