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

..

__init__.py

[LLM] First commit the llm deployment code

2025-06-09 19:20:15 +08:00

dcu_worker.py

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

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

eplb.py

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

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

experts_manager.py

[Feature] Support_eplb (#2997)

2025-07-24 20:22:45 +08:00

gcu_model_runner.py

[GCU] Update to develop (#2988)

2025-07-24 19:30:52 +08:00

gcu_worker.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00

gpu_model_runner.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

gpu_worker.py

[BugFix] fix multinode deployment (#2977)

2025-07-24 15:04:04 +08:00

iluvatar_model_runner.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00

iluvatar_worker.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00

model_runner_base.py

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

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

output.py

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

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

utils.py

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

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

worker_base.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00

worker_process.py

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

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

xpu_model_runner.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00

xpu_worker.py

[LLM] update function name (#2985)

2025-07-24 15:03:40 +08:00