RAM 528c55776e [Graph Optimization][Speculative Decoding] Fix the bug of CUDAGraph + MTP + EP (#4456) ...

* Fix MTP dummy run bug

* Target Model and Draft Model using the same flag

* In mtp replace use_cudagraph as step_use_cudagraph

2025-10-20 10:38:55 +08:00

..

__init__.py

[LLM] First commit the llm deployment code

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

dcu_model_runner.py

[FDConfig]Remove splitwise_role and engine_worker_queue_port in FDConfig (#4147)

2025-09-19 17:01:52 +08:00

dcu_worker.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

eplb.py

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

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

experts_manager.py

fix typos (#3684)

2025-09-01 17:50:17 +08:00

gcu_model_runner.py

[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362)

2025-10-17 10:40:59 +08:00

gcu_worker.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

gpu_model_runner.py

[Graph Optimization][Speculative Decoding] Fix the bug of CUDAGraph + MTP + EP (#4456)

2025-10-20 10:38:55 +08:00

gpu_worker.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

hpu_model_runner.py

[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362)

2025-10-17 10:40:59 +08:00

hpu_worker.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

iluvatar_model_runner.py

[Iluvatar GPU] Adapt VL model (#4313)

2025-10-17 16:13:38 +08:00

iluvatar_worker.py

[Iluvatar GPU] Adapt VL model (#4313)

2025-10-17 16:13:38 +08:00

metax_model_runner.py

[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362)

2025-10-17 10:40:59 +08:00

metax_worker.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

model_runner_base.py

[FDConfig]Remove max_num_batched_tokens/max_num_seqs in parallel config (#4116)

2025-09-17 10:43:35 +08:00

output.py

[Feature] support pooling model dummy_run (#4345)

2025-10-17 13:30:55 +08:00

utils.py

fix typos (#3684)

2025-09-01 17:50:17 +08:00

worker_base.py

[FDConfig]Remove splitwise_role and engine_worker_queue_port in FDConfig (#4147)

2025-09-19 17:01:52 +08:00

worker_process.py

[FDConfig]Remove reasoning_parser/guided_decoding_backend/disable_any_whitespace/device_ids in FDConfig (#4362)

2025-10-17 10:40:59 +08:00

xpu_model_runner.py

[FDConfig]Remove total_block_num/dtype/block_size/enc_dec_block_num in ParallelConfig (#4400)

2025-10-16 20:00:37 +08:00

xpu_worker.py

[XPU] abstract a hardware-agnostic operator wrapper for prefix cache and specify xpu device id definition (#4455)

2025-10-17 14:05:33 +08:00