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

[BugFix] fix deepseek torchair precision (#3624)

Browse Source 
### What this PR does / why we need it?
The precision of deepseek torchair is broken by #3465 , which due to the
origin patch or rmsnorm in torchair. This PR fixes the precision of
deepseek torchair

### 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/v0.11.0

Signed-off-by: hust17yixuan <303660421@qq.com>
This commit is contained in:
Wang Yixuan
2025-10-23 15:41:50 +08:00
committed by GitHub
parent f06a6cad1b
commit 2584f97217
2 changed files with 34 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/torchair/utils.py
View File

@@ -229,10 +229,12 @@ def torchair_ops_patch():
AscendDeepseekScalingRotaryEmbedding.__init__ = deepseek_rope_init_func # type: ignore[method-assign]
AscendDeepseekScalingRotaryEmbedding.forward = native_rope_deepseek_forward # type: ignore[method-assign]
AscendRMSNorm.__init__ = torchair_layernorm.torchair_rmsnorm_init_ # type: ignore[method-assign]
AscendRMSNorm.forward_oot = torchair_layernorm.torchair_rmsnorm_forward_oot # type: ignore[method-assign]
AscendSiluAndMul.forward_oot = torchair_activation.torchair_silu_and_mul_forward_oot # type: ignore[method-assign]
AscendVocabParallelEmbedding.forward = vocab_embedding_forward # type: ignore[method-assign]
def super_kernel(prefix: str, option: str, enabled: bool = True):
return _super_kernel(prefix, option) if enabled else nullcontext()
return _super_kernel(prefix, option) if enabled else nullcontext()