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

Revert PTA upgrade PR (#3352)

Browse Source 
we notice that torch npu 0919 doesn't work. This PR revert related
change which rely on 0919 version.
Revert PR: #3295  #3205  #3102 

Related: #3353

- vLLM version: v0.11.0
This commit is contained in:
wangxiyuan
2025-10-10 14:09:53 +08:00
committed by GitHub
parent 601a37aeff
commit ba19dd3183
15 changed files with 57 additions and 312 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
vllm_ascend/ascend_forward_context.py
View File

@@ -156,14 +156,12 @@ def set_ascend_forward_context(
# Once the necessary conditions are met, support for MOE models will also be added.
from vllm_ascend.quantization.quant_config import AscendQuantConfig
addrmsnorm_quant_fusion_enabled = isinstance(vllm_config.quant_config, AscendQuantConfig) and \
vllm_config.model_config.hf_config.model_type in ["llama", "qwen2", "qwen3", "qwen3_moe"] and \
vllm_config.model_config.hf_config.model_type in ["llama", "qwen2", "qwen3"] and \
forward_context.layer_idx is not None
if addrmsnorm_quant_fusion_enabled:
forward_context.model_instance = model_instance
forward_context.num_hidden_layers = vllm_config.model_config.hf_config.num_hidden_layers
forward_context.fusion_linear = "gate_up_dense" if forward_context.layer_idx == 0 else "qkv_dense"
if vllm_config.model_config.hf_config.model_type == "qwen3_moe":
forward_context.fusion_linear = "gate_moe" if forward_context.layer_idx == 0 else "qkv_moe"
forward_context.addrmsnorm_quant_fusion_enabled = addrmsnorm_quant_fusion_enabled
if num_tokens is None and attn_metadata is not None: