Skip to content

Commit d404e02

Browse files
Update DSv4 GB300 Dynamo SGLang MTP image (#1637)
* chore: update dsv4 gb300 dynamo sglang mtp image * chore: log dsv4 gb300 sglang mtp image bump --------- Co-authored-by: Bryan Shan <58582368+Oseltamivir@users.noreply.github.com>
1 parent 7d4063d commit d404e02

2 files changed

Lines changed: 8 additions & 1 deletion

File tree

.github/configs/nvidia-master.yaml

Lines changed: 1 addition & 1 deletion
Original file line numberDiff line numberDiff line change
@@ -9067,7 +9067,7 @@ glm5-fp8-b200-dynamo-sglang:
90679067

90689068
# MTP variant of dsv4-fp4-gb300-dynamo-sglang.
90699069
dsv4-fp4-gb300-dynamo-sglang-mtp:
9070-
image: lmsysorg/sglang:nightly-dev-cu13-20260509-9ee83034
9070+
image: lmsysorg/sglang:nightly-dev-20260527-14f81a67
90719071
model: deepseek-ai/DeepSeek-V4-Pro
90729072
model-prefix: dsv4
90739073
runner: gb300-cw

perf-changelog.yaml

Lines changed: 7 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -3404,6 +3404,13 @@
34043404
- "Add DeepSeek-V4-Pro FP4 MI355X ATOM MTP3 benchmark; image rocm/atom:rocm7.2.4_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.3"
34053405
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1627
34063406

3407+
- config-keys:
3408+
- dsv4-fp4-gb300-dynamo-sglang-mtp
3409+
description:
3410+
- "Update SGLang image from nightly-dev-cu13-20260509-9ee83034 to nightly-dev-20260527-14f81a67"
3411+
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1637
3412+
3413+
34073414
- config-keys:
34083415
- minimaxm2.5-fp4-gb200-dynamo-vllm
34093416
description:

0 commit comments

Comments
 (0)