whx 211d4b9da4 [BugFix] Fix mlapo accuracy problem related with weight processing. (#3857) ...

This PR fixes a mlapo accuracy problem related with weight processing.
Furthermore, modify mlapo related e2e test with quantized deepseek model
to make it effective.

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-10-30 00:35:50 +08:00

..

ops

remove redundant params in mla_preprocess kernel (#3530)

2025-10-21 19:20:13 +08:00

spec_decode_v1

[BugFix] Fix mlapo accuracy problem related with weight processing. (#3857)

2025-10-30 00:35:50 +08:00

__init__.py

[CI] Add unit test framework (#1201)

2025-06-16 18:32:28 +08:00

test_aclgraph.py

[Test] Temporarily skip flaky ACL graph test (#3577)

2025-10-21 17:16:15 +08:00

test_ascend_scheduler.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_bge_model.py

[Feat] Supports Aclgraph for bge-m3 (#3171)

2025-10-14 23:07:45 +08:00

test_camem.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_chunked.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_embedding_aclgraph.py

[Feat] Supports Aclgraph for bge-m3 (#3171)

2025-10-14 23:07:45 +08:00

test_embedding.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_guided_decoding.py

[Misc] Clean up useless patch (#3320)

2025-10-09 14:07:26 +08:00

test_ilama_lora.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_multistream_overlap_shared_expert.py

[Cherry-pick] Port MoE multi-stream fix to v0.11.0-dev (#3753)

2025-10-25 15:51:43 +08:00

test_profile_execute_duration.py

Refactor e2e CI (#2276)

2025-09-02 09:02:22 +08:00

test_quantization.py

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +08:00

test_sampler.py

Refactor e2e CI (#2276)

2025-09-02 09:02:22 +08:00

test_vlm.py

[BugFix] cherry-pick PR 3736 to v0.11.0-dev (#3737)

2025-10-25 10:35:14 +08:00