chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 11 Packages Projects Releases Wiki Activity

[NPU]MindSpore backend support eagle3 (#17098)

Browse Source 
Co-authored-by: wangtiance <tiancew@qq.com>
Co-authored-by: Tiance Wang <wangtiance@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
This commit is contained in:
Xuhao Zhang
2026-03-11 09:11:19 +03:00
committed by GitHub
co-authored by wangtiance Tiance Wang gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> ronnie_zheng
parent 18cfeabd33
commit 57b093dc34
3 changed files with 63 additions and 14 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/speculative/eagle_worker_v2.py
+3
View File
@@ -254,6 +254,9 @@ class EagleDraftWorker(BaseDraftWorker):
if self.server_args.disable_cuda_graph:
return
if self.server_args.model_impl == "mindspore":
return
Device2DraftCudaGraphRunner = {
"npu": EAGLEDraftNpuGraphRunner,
"cuda": EAGLEDraftCudaGraphRunner,