yiz-liu 2c7dd85fd8 [Fix] Fix the token-wise padding mechanism (#1300) ...

### What this PR does / why we need it?
Fix the token-wise padding mechanism.

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>

2025-06-20 14:46:17 +08:00

..

__init__.py

port deepseekv2 and mtp to main branch (#429)

2025-04-19 17:38:18 +08:00

cache_engine.py

[Misc] Refactor additional_config (#1029)

2025-06-05 16:28:01 +08:00

draft_model_runner.py

[CI] upgrade vllm to 0.8.5 (#715)

2025-04-30 09:15:50 +08:00

model_runner_v1.py

[Fix] Fix the token-wise padding mechanism (#1300)

2025-06-20 14:46:17 +08:00

model_runner.py

Avoid unfused Transpose in DeepSeekV3 EP256 MoE layer (#1091)

2025-06-07 14:28:20 +08:00

mtp_proposer_v1.py

[MTP][V1] Adapt mtp with graph mode in v1. (#1023)

2025-06-09 22:21:42 +08:00

multi_step_runner.py

[Performance]: Custom AscendC Kernel of Multi-Step Prepare Input (#814)

2025-05-20 09:31:30 +08:00

multi_step_worker.py

[MLA][Graph] Improve assertion on Graph mode with MLA (#933)

2025-06-10 22:26:53 +08:00

pooling_model_runner.py

[MISC] Clean up torch_npu (#688)

2025-04-29 18:03:38 +08:00

worker_v1.py

[refactor] Refactoring AscendFusedMoE (#1229)

2025-06-17 17:49:03 +08:00

worker.py

[Misc] Adjust the default profiler configuration (#1097)

2025-06-06 20:25:59 +08:00