zhangxinyuehfad 71e9b379c8 [Bugfix] Fix Qwen2.5-Omni-7B accuarcy test (#4556) ...

### What this PR does / why we need it?
Fix Qwen2.5-Omni-7B accuarcy test
issue：https://github.com/vllm-project/vllm-ascend/issues/4480
Depends on : https://github.com/vllm-project/vllm-ascend/pull/4534

- vLLM version: v0.11.2
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.2

Signed-off-by: hfadzxy <starmoon_zhang@163.com>

2025-12-02 09:20:05 +08:00

..

fused_moe

[EPLB][Ops] Integerate grouped_matmul_swiglu_quant_weight_nz_tensor_list operator into dynamic EPLB (#4216)

2025-11-30 22:52:05 +08:00

triton

【OPS】qwen3-next support triton chunk_gated_delta_rule ops (#4070)

2025-11-28 20:55:43 +08:00

__init__.py

[Refactor] [MoE] Rename moe-related classes & files (#3646)

2025-10-25 11:22:03 +08:00

activation.py

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

attention.py

remove useless code (#3685)

2025-10-24 16:29:08 +08:00

expert_load_balancer.py

eplb redundant expert bugfix (#4291)

2025-11-21 14:24:35 +08:00

layernorm.py

[Bugfix] Fix Qwen2.5-Omni-7B accuarcy test (#4556)

2025-12-02 09:20:05 +08:00

linear_op.py

[Feat] flashcomm_v2 optim solution (#3232)

2025-11-10 11:01:45 +08:00

linear.py

[Bugfix] Remove ModelSlim-"M4 Quantization". (#4589)

2025-12-01 23:45:02 +08:00

mla.py

Move mla to ops module (#4575)

2025-11-29 18:36:55 +08:00

register_custom_ops.py

[Bugfix] Fix Qwen2.5-Omni-7B accuarcy test (#4556)

2025-12-02 09:20:05 +08:00

rotary_embedding.py

[refact] unified soc_version code (#4359)

2025-11-26 14:28:55 +08:00

vocab_parallel_embedding.py

[Bugfix] Fix MTP support for lmhead_tensor_parallel_size (#3915)

2025-10-31 10:30:28 +08:00

weight_prefetch.py

Update torch-npu version to 2.7.1 (#3896)

2025-10-31 17:16:31 +08:00