starkwj 31868639fd fix multiproc executor determine kv cache memory

2026-04-24 08:31:54 +00:00

..

__init__.py

adapt to vllm-ascend v0.18.0rc1

2026-04-21 03:05:32 +00:00

patch_balance_schedule.py

[Patch] Fix balance scheduling (#7611)

2026-03-25 08:57:06 +08:00

patch_core.py

fix multiproc executor determine kv cache memory

2026-04-24 08:31:54 +00:00

patch_distributed.py

[Feature]: Support 310P device run qwen2.5/3 dense and qwen2.5vl models (#5776)

2026-01-17 11:49:18 +08:00

patch_executor.py

fix multiproc executor determine kv cache memory

2026-04-24 08:31:54 +00:00

patch_fusion_matcher_compat_ops.py

[Main2Main] Upgrade vLLM to 0303 (#6944)

2026-03-06 09:08:52 +08:00

patch_glm_tool_call_parser.py

[Bugfix][Platform] Fix GLM47 tool-call finish backfill (#7710)

2026-03-28 09:15:04 +08:00

patch_kv_cache_interface.py

[bugfix] restore pr-7029 and fix patch error (#7294)

2026-03-16 15:39:42 +08:00

patch_mamba_config_310.py

[CI] Add pre-commit check for patch logger (#7446)

2026-03-19 16:53:20 +08:00

patch_mamba_config.py

[Misc]fix logger which does not take effects in patches (#7402)

2026-03-18 17:13:12 +08:00

patch_minimax_m2_config.py

[v0.18.0] Apply Eagle3 to MiniMax-M2.5 (#7619) (#7714)

2026-03-27 18:33:29 +08:00

patch_minimax_usage_accounting.py

fix(platform): reimplement MiniMax usage accounting patch (#7835)

2026-03-31 16:27:00 +08:00

patch_multiproc_executor.py

upgrade to 0.18.0 (#7502)

2026-03-21 16:05:38 +08:00

patch_sched_yield.py

[Lint]Style: Convert vllm-ascend/ to ruff format(Batch #6) (#6001)

2026-01-24 22:08:33 +08:00

patch_torch_accelerator.py

Main2main upgrade to vllm 0317 afternoon (#7409)

2026-03-18 23:24:27 +08:00