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

remove useless patch (#4699)

Browse Source 
patach_config is useless now. Let's remove it


- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>
This commit is contained in:
wangxiyuan
2025-12-08 11:02:42 +08:00
committed by GitHub
parent 866347a621
commit 0b65ac6c4b
21 changed files with 30 additions and 277 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
vllm_ascend/compilation/acl_graph.py
View File

@@ -257,7 +257,7 @@ def update_mla_attn_params(update_stream, forward_context, runtime_shape,
softmax_lse) = param
seq_lens_list = forward_context.attn_metadata[
key].decode.seq_lens_list
if speculative_config and speculative_config.method == "deepseek_mtp" \
if speculative_config and speculative_config.method == "mtp" \
and not forward_context.is_mtp_model:
actual_seq_lengths = forward_context.attn_metadata[
key].decode.actual_seq_lengths_q