realliujiaxu 778cb72556 fix bug when rotary_dim is not 128 (#2847) ...

### What this PR does / why we need it?
`torch_npu.npu_apply_rotary_pos_emb` only support head_size and
rotary_dim equal 128. Error occurs when running GLM

### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?

- vLLM version: main
- vLLM main:
404c85ca72

Signed-off-by: realliujiaxu <realliujiaxu@163.com>

2025-09-12 09:49:36 +08:00

..

moe

Refactor tensor_parallel and comm_utils (#2814)

2025-09-11 21:26:36 +08:00

__init__.py

[main] flashcomm_v1 optim in Qwen Dense Models (#2802)

2025-09-08 22:52:24 +08:00

activation.py

[main] mlp weight prefetch in Qwen Dense Models (#2816)

2025-09-11 21:20:09 +08:00

attention.py

Disaggregate prefill for kv cache register style (#950)

2025-07-26 17:15:47 +08:00

common_fused_moe.py

fix ascend fused moe spelling error (#2863)

2025-09-11 14:35:46 +08:00

expert_load_balancer.py

Add static EPLB (#1116)

2025-06-09 19:28:11 +08:00

fused_moe.py

[main] [refactor] refactor common_fused_moe.py (#2706)

2025-09-08 20:09:50 +08:00

layernorm.py

[Quantization] register AscendQuantRMSNorm for quantization (#2856)

2025-09-11 23:14:02 +08:00

linear.py

[main] mlp weight prefetch in Qwen Dense Models (#2816)

2025-09-11 21:20:09 +08:00

register_custom_ops.py

[main] mlp weight prefetch in Qwen Dense Models (#2816)

2025-09-11 21:20:09 +08:00

rotary_embedding.py

fix bug when rotary_dim is not 128 (#2847)

2025-09-12 09:49:36 +08:00

sequence_parallel.py

【main】SP For Qwen3 MoE (#2209)

2025-08-07 09:15:49 +08:00

vocab_parallel_embedding.py

[2/N][Refactor][Quantization] clean quantization patch (#2785)

2025-09-08 17:31:53 +08:00