From 7b227424050e2cdd1635abe6642384dcd914c7b2 Mon Sep 17 00:00:00 2001 From: hshrivastava-droid Date: Tue, 14 Apr 2026 23:50:53 -0700 Subject: [PATCH 1/2] update sglang container --- .github/configs/nvidia-master.yaml | 2 +- perf-changelog.yaml | 6 ++++++ 2 files changed, 7 insertions(+), 1 deletion(-) diff --git a/.github/configs/nvidia-master.yaml b/.github/configs/nvidia-master.yaml index 27ee51eef..c4c9693a0 100644 --- a/.github/configs/nvidia-master.yaml +++ b/.github/configs/nvidia-master.yaml @@ -2037,7 +2037,7 @@ qwen3.5-fp8-h200-sglang-mtp: - { tp: 8, ep: 8, conc-start: 4, conc-end: 128, spec-decoding: mtp } glm5-fp8-h200-sglang: - image: lmsysorg/sglang:glm5-hopper + image: lmsysorg/sglang:v0.5.10.post1-cu130 model: zai-org/GLM-5-FP8 model-prefix: glm5 runner: h200 diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 746d0645d..53fa4d4b1 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -1348,3 +1348,9 @@ description: - "Enable SGLANG_ENABLE_SPEC_V2=1 for Qwen3.5 FP8 H200 SGLang MTP" pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1017 + +- config-keys: + - glm5-fp8-h200-sglang + description: + - "Update SGLang image from glm5-hopper to v0.5.10.post1-cu130" + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX From 295e1df88e40e4516fdba1e231656d63d5d6ded0 Mon Sep 17 00:00:00 2001 From: hshrivastava-droid Date: Wed, 15 Apr 2026 14:43:53 -0700 Subject: [PATCH 2/2] update PR number --- perf-changelog.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/perf-changelog.yaml b/perf-changelog.yaml index 53fa4d4b1..214bb3915 100644 --- a/perf-changelog.yaml +++ b/perf-changelog.yaml @@ -1353,4 +1353,4 @@ - glm5-fp8-h200-sglang description: - "Update SGLang image from glm5-hopper to v0.5.10.post1-cu130" - pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/XXX + pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1033