Skip to content

[Klaud Cold] Update glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp SGLang image to v0.5.19-cu130 / 将 glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp 的 SGLang 镜像更新至 v0.5.19-cu130 #2992

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
Klaud-Cold wants to merge 3 commits into from
Closed

[Klaud Cold] Update glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp SGLang image to v0.5.19-cu130 / 将 glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp 的 SGLang 镜像更新至 v0.5.19-cu130 #2992

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
3 commits
Select commit Hold shift + click to select a range
10aa0fe
chore: bump GLM-5.2 GB200 AgentX MTP SGLang image to v0.5.19-cu130
Klaud-Cold Sep 11, 2026
15fdf33
chore: add perf-changelog entry for GLM-5.2 GB200 AgentX MTP image bump
Klaud-Cold Sep 11, 2026
e621c62
chore: merge main into the GLM-5.2 GB200 AgentX MTP image bump
Klaud-Cold Sep 11, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions ...srt-slurm-recipes/sglang/glm5.2/gb200-fp4/agentic/disagg-gb200-1p4d-dep8-tp4-c48-mtp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@ identity:
repo: nvidia/GLM-5.2-NVFP4
revision: aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa
container:
image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
image: lmsysorg/sglang:v0.5.19-cu130@sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9
frameworks:
dynamo: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
sglang: nightly-dev-cu13-20260805-211ee642
dynamo: "1.5.0.dev20260910"
sglang: "0.5.19"
resources:
gpu_type: gb200
gpus_per_node: 4
Expand All @@ -35,8 +35,8 @@ frontend:
active-prefill-tokens-threshold: None
active-prefill-tokens-threshold-frac: None
dynamo:
hash: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
install: true
wheel: "1.5.0.dev20260910"
backend:
type: sglang
prefill_environment:
Expand Down
8 changes: 4 additions & 4 deletions ...srt-slurm-recipes/sglang/glm5.2/gb200-fp4/agentic/disagg-gb200-1p6d-dep8-tp4-c45-mtp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@ identity:
repo: nvidia/GLM-5.2-NVFP4
revision: aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa
container:
image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
image: lmsysorg/sglang:v0.5.19-cu130@sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9
frameworks:
dynamo: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
sglang: nightly-dev-cu13-20260805-211ee642
dynamo: "1.5.0.dev20260910"
sglang: "0.5.19"
resources:
gpu_type: gb200
gpus_per_node: 4
Expand All @@ -35,8 +35,8 @@ frontend:
active-prefill-tokens-threshold: None
active-prefill-tokens-threshold-frac: None
dynamo:
hash: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
install: true
wheel: "1.5.0.dev20260910"
backend:
type: sglang
prefill_environment:
Expand Down
8 changes: 4 additions & 4 deletions ...-slurm-recipes/sglang/glm5.2/gb200-fp4/agentic/disagg-gb200-2p1d-dep8-dep16-c128-mtp.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,10 +8,10 @@ identity:
repo: nvidia/GLM-5.2-NVFP4
revision: aec724e8c7b8ee9db3b48c01c320f63f9cdaf8aa
container:
image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
image: lmsysorg/sglang:v0.5.19-cu130@sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9
frameworks:
dynamo: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
sglang: nightly-dev-cu13-20260805-211ee642
dynamo: "1.5.0.dev20260910"
sglang: "0.5.19"
resources:
gpu_type: gb200
gpus_per_node: 4
Expand All @@ -35,8 +35,8 @@ frontend:
active-prefill-tokens-threshold: None
active-prefill-tokens-threshold-frac: None
dynamo:
hash: 71eb001e17fa73c742f0afe1a6ed96836cb135fd
install: true
wheel: "1.5.0.dev20260910"
backend:
type: sglang
prefill_environment:
Expand Down
4 changes: 2 additions & 2 deletions configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9193,15 +9193,15 @@ glm5.2-fp4-gb200-dynamo-sglang-agentic-disagg:
# GLM-5.2 NVFP4 GB200 AgentX disaggregated variants use the committed
# thinking-on golden acceptance length for two speculative tokens.
glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp:
image: lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642
image: lmsysorg/sglang:v0.5.19-cu130@sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9
model: nvidia/GLM-5.2-NVFP4
model-prefix: glm5.2
runner: cluster:gb200-nv
precision: fp4
framework: dynamo-sglang
router:
name: dynamo-router
version: 1.2.1
version: 1.5.0.dev20260910
kv-p2p-transfer: nixl
multinode: true
disagg: true
Expand Down
8 changes: 8 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7179,3 +7179,11 @@
description:
- "Use the pinned SGLang nightly-dev-cu13-20260901-07c8f729 image with FlashInfer 0.6.18, which includes the BF16 TRTLLM MoE allocation fix for small-batch Blackwell execution. Model, TP8, HiCache, MTP settings and concurrency grid are unchanged."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2994

- config-keys:
- glm5.2-fp4-gb200-dynamo-sglang-agentic-mtp
description:
- "Update the SGLang image from lmsysorg/sglang:nightly-dev-cu13-20260805-211ee642 (2026-08-05 cu13 dev nightly, build commit sgl-project/sglang@211ee642) to the digest-pinned v0.5.19 release lmsysorg/sglang:v0.5.19-cu130@sha256:d6e7288627be8b02be88e4bba38e73f6d50e2826869f753c13a4c4385ab3eda9 (build commit sgl-project/sglang@0bcd822377da7b5718e674eaf9c870d349424dd1, Docker Hub last pushed 2026-09-04T22:50:19Z)."
- "Move the three disaggregated recipes' Dynamo install from source commit 71eb001e17fa73c742f0afe1a6ed96836cb135fd to the ai-dynamo 1.5.0.dev20260910 wheel, which carries the ServerArgs.get_model_config()/use_mla_backend() compatibility shim for SGLang #36972 (ai-dynamo/dynamo#14234) and pins sglang==0.5.19 (ai-dynamo/dynamo#14151); align recipe identity.frameworks and the master router version to 1.5.0.dev20260910 / 0.5.19."
- "Topology, MTP settings, HiCache DRAM offload, NIXL KV transfer, concurrency 45/48/128 and NVIDIA/srt-slurm v1.0.50 are unchanged."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2992
Loading