`nemo_rl.modelopt.models.generation.vllm_quant_worker`#

Module Contents#

Classes#

`VllmQuantGenerationWorker`
`VllmQuantAsyncGenerationWorker`

Functions#

`_quant_cfg_for_worker_env`
`_configure_quant_engine_kwargs`

Data#

_EXTRA_ENV_VARS

API#

nemo_rl.modelopt.models.generation.vllm_quant_worker._EXTRA_ENV_VARS#: (‘VLLM_QUANT_CFG’, ‘VLLM_MODELOPT_REAL_QUANT’, ‘PYTHONPATH’)

nemo_rl.modelopt.models.generation.vllm_quant_worker._quant_cfg_for_worker_env(quant_cfg: str) → str#

nemo_rl.modelopt.models.generation.vllm_quant_worker._configure_quant_engine_kwargs( cfg: nemo_rl.models.generation.vllm.config.VllmConfig, llm_kwargs: dict[str, Any], ) → None#

class nemo_rl.modelopt.models.generation.vllm_quant_worker.VllmQuantGenerationWorker(*args, **kwargs)#

Bases: nemo_rl.models.generation.vllm.vllm_worker.VllmGenerationWorkerImpl

_create_engine(llm_kwargs: dict[str, Any]) → None#

get_quantizer_stats() → dict[str, Any]#: Return quantizer statistics. Mirrors MegatronQuantPolicyWorker.get_quantizer_stats().

get_weight_snapshot(name: str) → Any#: Return a CPU copy of a named parameter for before/after comparison.

class nemo_rl.modelopt.models.generation.vllm_quant_worker.VllmQuantAsyncGenerationWorker(*args, **kwargs)#

Bases: nemo_rl.models.generation.vllm.vllm_worker_async.VllmAsyncGenerationWorkerImpl

_create_engine(llm_kwargs: dict[str, Any]) → None#

async get_quantizer_stats() → dict[str, Any]#: Return quantizer statistics. Mirrors MegatronQuantPolicyWorker.get_quantizer_stats().

async get_weight_snapshot(name: str) → Any#: Return a CPU copy of a named parameter for before/after comparison.