Skip to content

Commit 48d98aa

Browse files
authored
Update glm5-fp4-b300-sglang SGLang image to v0.5.11-cu130
1 parent b286b28 commit 48d98aa

2 files changed

Lines changed: 7 additions & 1 deletion

File tree

.github/configs/nvidia-master.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -2252,7 +2252,7 @@ glm5-fp4-b200-sglang-mtp:
22522252
# does not have a B300-specific recipe, so this config reuses the existing
22532253
# GLM-5 FP4 B200 SGLang recipe as-is until B300-specific tuning is available.
22542254
glm5-fp4-b300-sglang:
2255-
image: lmsysorg/sglang:v0.5.10.post1-cu130
2255+
image: lmsysorg/sglang:v0.5.11-cu130
22562256
model: nvidia/GLM-5-NVFP4
22572257
model-prefix: glm5
22582258
runner: b300

perf-changelog.yaml

Lines changed: 6 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -2430,3 +2430,9 @@
24302430
description:
24312431
- "Update SGLang image from v0.5.10.post1-cu130 to v0.5.11-cu130"
24322432
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1346
2433+
2434+
- config-keys:
2435+
- glm5-fp4-b300-sglang
2436+
description:
2437+
- "Update SGLang image from v0.5.10.post1-cu130 to v0.5.11-cu130"
2438+
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1329

0 commit comments

Comments
 (0)