Mengqing Cao 7a325b2e2d [Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867) ...

### What this PR does / why we need it?
this PR fix CI failure broken by vllm.
1. add moe_config for fused_moe
2. adjust the change for kv cache group from vllm. currently vllm-ascend
doesn't support this feature. this is just a quick fix for backward
compatibility

fix: #872

---------

Signed-off-by: MengqingCao <cmq0113@163.com>

2025-05-16 12:14:55 +08:00

..

__init__.py

port deepseekv2 and mtp to main branch (#429)

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

cache_engine.py

support deepseek quant & mix-parallel with graphmode (#585)

2025-04-23 16:23:25 +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

[Bugfix][Model] Fix fusedmoe and make modelrunner_v1 compatible with latest vllm (#867)

2025-05-16 12:14:55 +08:00

model_runner.py

[Core] Support the features of prefix cache and chunked prefill in v0/v1 (#782)

2025-05-09 16:39:28 +08:00

multi_step_runner.py

[CI] upgrade vllm to 0.8.5 (#715)

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

multi_step_worker.py

support multistep decode (#299)

2025-03-11 19:20:06 +08:00

pooling_model_runner.py

[MISC] Clean up torch_npu (#688)

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

worker_v1.py

[Bugfix] Tweak distributed process group initialization and add dummy… (#816)

2025-05-12 17:31:29 +08:00

worker.py

[Disaggregated Prefill] P2P Disaggregated Prefill based on llm_datadist (#694)

2025-05-01 22:31:36 +08:00