chen d233e3c97c [Precision] Change lm_head layer running in float32 (#3596) ...

* support lm_head fp32 bf16 fp16

* delete print

* code check

* check

* check

* code check

* check

* check

2025-08-26 20:20:06 +08:00

..

sched

[Bug fix] Fix block num in scheduler v1 for release2.0.4 (#3314)

2025-08-11 23:55:45 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

args_utils.py

[Precision] Change lm_head layer running in float32 (#3596)

2025-08-26 20:20:06 +08:00

config.py

[Precision] Change lm_head layer running in float32 (#3596)

2025-08-26 20:20:06 +08:00

engine.py

[Precision] Change lm_head layer running in float32 (#3596)

2025-08-26 20:20:06 +08:00

expert_service.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

kv_cache_interface.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

request.py

[Cherry-pick] FIx bug for scheduler V1 (#3167)

2025-08-04 17:08:12 +08:00

resource_manager.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

sampling_params.py

[Feature] Add temp_scaled_logprobs and top_p_normalized_logprobs parameters for logits and logprobs post processing (#3536)

2025-08-25 14:11:18 +08:00