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

[diffusion] multi-platform: support diffusion on amd and fix encoder loading on MI325 (#13760)

Browse Source 
Co-authored-by: Sabre Shao <sabre.shao@amd.com>
Co-authored-by: Yusheng (Ethan) Su <yushengsu.thu@gmail.com>
Co-authored-by: Hubert Lu <Hubert.Lu@amd.com>
Co-authored-by: xsun <sunxiao04@gmail.com>
This commit is contained in:
Yuzhen Zhou
2025-12-19 02:38:46 -05:00
committed by GitHub
parent f2d64e6782
commit 4bf06635fc
34 changed files with 823 additions and 72 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
python/sglang/multimodal_gen/envs.py
View File

@@ -285,6 +285,10 @@ environment_variables: dict[str, Callable[[], Any]] = {
if os.getenv("SGLANG_DIFFUSION_ATTENTION_CONFIG", None) is None
else os.path.expanduser(os.getenv("SGLANG_DIFFUSION_ATTENTION_CONFIG", "."))
),
# Optional override to force a specific attention backend (e.g. "aiter")
"SGLANG_DIFFUSION_ATTENTION_BACKEND": lambda: os.getenv(
"SGLANG_DIFFUSION_ATTENTION_BACKEND"
),
# Use dedicated multiprocess context for workers.
# Both spawn and fork work
"SGLANG_DIFFUSION_WORKER_MULTIPROC_METHOD": lambda: os.getenv(