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

[Feature] support aclgraph for model runner v2 (#7110)

Browse Source 
### What this PR does / why we need it?
This PR aims to support aclgraph for model runner v2, please see RFC
#5208. The PR contains these modifications:
- adapt to newest commit of vllm main branch.
- supply a unified interface of extra forward context for both model
runner v1 and model runner v2.
- implement graph mode for main model. 

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

### How was this patch tested?

- vLLM version: v0.16.0
- vLLM main:
4034c3d32e

---------

Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
This commit is contained in:
Ronald
2026-03-13 09:11:46 +08:00
committed by GitHub
parent 1f71da80eb
commit c980e68d40
52 changed files with 840 additions and 309 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/worker/v2/spec_decode/eagle.py
View File

@@ -23,7 +23,7 @@ import torch
import vllm
from vllm.config import VllmConfig
from vllm.v1.worker.gpu.input_batch import InputBatch
from vllm.v1.worker.gpu.spec_decode.eagle import EagleSpeculator
from vllm.v1.worker.gpu.spec_decode.eagle.speculator import EagleSpeculator
from vllm_ascend.attention.attention_v1 import AscendAttentionState
from vllm_ascend.worker.v2.attn_utils import build_attn_metadata