chenchenghao/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

[Feature][MM] split the images of one request into multiparts (#11828)

Browse Source 
Signed-off-by: Xuchun Shang <xuchun.shang@linux.alibaba.com>
Signed-off-by: Kun(llfl) <i@imux.top>
Signed-off-by: Xuchun Shang <xuchun.shang@gmail.com>
Co-authored-by: Teng Ma <sima.mt@alibaba-inc.com>
Co-authored-by: Kun(llfl) <llfl@linux.alibaba.com>
Co-authored-by: Kun(llfl) <i@imux.top>
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
This commit is contained in:
Xuchun Shang
2025-12-24 11:22:04 +08:00
committed by GitHub
co-authored by Teng Ma Kun Kun liusy58
parent e7b09efc0a
commit 3bf07c684f
3 changed files with 255 additions and 15 deletions
Download Patch File Download Diff File Expand all files Collapse all files
python/sglang/srt/environ.py
+3
View File
@@ -350,6 +350,9 @@ class Envs:
SGLANG_MM_FEATURE_CACHE_MB = EnvInt(4 * 1024)
SGLANG_MM_ITEM_MEM_POOL_RECYCLE_INTERVAL_SEC = EnvFloat(0.05)
# MM splitting behavior control
SGLANG_ENABLE_MM_SPLITTING = EnvBool(False)
# Release & Resume Memory
SGLANG_MEMORY_SAVER_CUDA_GRAPH = EnvBool(False)