EngineX/xc-llm-ascend
3
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

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

Browse Source 
### What this PR does / why we need it?
Flashcomm_v1 optim in Qwen Dense Models.

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

### How was this patch tested?
CI passed with new added/existing test.

- vLLM version: v0.10.1.1
- vLLM main:
5e537f45b4

Co-authored-by: 1024daniel <xxltju324@gmail.com>
This commit is contained in:
rjg-lyh
2025-09-08 22:52:24 +08:00
committed by GitHub
parent 4df8df5b94
commit 1bbb20ea13
11 changed files with 362 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
vllm_ascend/ops/__init__.py
View File

@@ -20,6 +20,7 @@ import torch
import vllm_ascend.ops.common_fused_moe # noqa
import vllm_ascend.ops.fused_moe # noqa
import vllm_ascend.ops.layernorm # noqa
import vllm_ascend.ops.register_custom_ops # noqa
import vllm_ascend.ops.vocab_parallel_embedding # noqa
from vllm_ascend.ops.activation import AscendQuickGELU, AscendSiluAndMul
from vllm_ascend.ops.rotary_embedding import (