[Feat][Graph] Support DeepSeek with ACL Graph (#2707)

### What this PR does / why we need it?
In memory of #677 , a long overdue milestone. Now DeepSeek V3/R1 should
be OK with ACL Graph.

### Does this PR introduce _any_ user-facing change?
None.

### How was this patch tested?
Working on it.

- vLLM version: v0.10.2
- vLLM main:
68dbde5dbb

---------

Signed-off-by: Yizhou Liu <liu_yizhou@outlook.com>
This commit is contained in:
yiz-liu
2025-09-16 17:50:17 +08:00
committed by GitHub
parent 3e60aa5483
commit 88ca8a051c
7 changed files with 64 additions and 42 deletions

View File

@@ -227,8 +227,9 @@ class NPUPlatform(Platform):
"When enabling piecewise aclgraph, please make sure compilation_config.level == CompilationLevel.PIECEWISE and compilation_config.cudagraph_mode == CUDAGraphMode.PIECEWISE"
compilation_config.set_splitting_ops_for_v1()
compilation_config.use_inductor = False
compilation_config.splitting_ops.extend(
["vllm.unified_ascend_attention_with_output"])
compilation_config.splitting_ops.extend([
"vllm.unified_ascend_attention_with_output", "vllm.mla_forward"
])
update_aclgraph_sizes(vllm_config)
else:
logger.info(