xc-llm-ascend

Files

realliujiaxu 74191864b7 [Perf] Delete redundant operations in model_runner and forward_context (#3677 )

### What this PR does / why we need it?

Remove redundant operations from `model_runner` and `forward_context`.
This optimization can significantly reduce the idle time (bubble) before
decoding when running models with small parameter counts (e.g.,
Qwen/Qwen2.5-0.5B).

Testing on 800I A2, bubble is reduced from 3.8ms to 2.8ms :
Before
<img width="1655" height="696" alt="image"
src="https://github.com/user-attachments/assets/d7608e52-2438-46dd-8fc9-391fd6274495"
/>

After
<img width="1607" height="774" alt="image"
src="https://github.com/user-attachments/assets/56daf081-2dba-4d2e-99d4-e055187d9806"
/>

### Does this PR introduce _any_ user-facing change?
No

### How was this patch tested?


- vLLM version: v0.11.0rc3
- vLLM main:
https://github.com/vllm-project/vllm/commit/releases/v0.11.1

---------

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

2025-10-29 15:59:55 +08:00

fused_moe

[Perf] Delete redundant operations in model_runner and forward_context (#3677 )

2025-10-29 15:59:55 +08:00

__init__.py

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

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

activation.py

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

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

attention.py

remove useless code (#3685 )