wangxiyuan 68fb63428b [CI] Patch torch.library.infer_schema for fused moe ops to fix CI (#854) ...

make sure pytorch infer_schema check is patched before some case which
using fused moe ops:
1. model register
2. quantization loading
3. fused moe ut

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>

2025-05-14 19:49:09 +08:00

..

compile

support aclgraph (#426)

2025-04-23 20:56:24 +08:00

e2e

[CI] Add e2e test frame work and doctest (#730)

2025-05-14 09:27:54 +08:00

multicard

[CI] Add deepseek-v2-lite test (#631)

2025-05-12 14:59:17 +08:00

ops

[CI] Patch torch.library.infer_schema for fused moe ops to fix CI (#854)

2025-05-14 19:49:09 +08:00

scheduler

[BugFix] Fix scheduler problems in last PR. (#558)

2025-04-18 08:49:48 +08:00

singlecard

[CI/UT] fix spec ut in vllm-ascend main and vllm main (#759)

2025-05-10 09:45:56 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00

conftest.py

[CI] Add qwen2.5-vl test (#643)

2025-04-24 17:12:12 +08:00

model_utils.py

[CI] Add qwen2.5-vl test (#643)

2025-04-24 17:12:12 +08:00

utils.py

[Bugfix] Fix output tensor shape in vanilla_chunked_prefill and update import paths for model_loader (#773)

2025-05-08 14:19:26 +08:00