Skip to content

[Klaud Cold] Update qwen3.5-fp4-gb300-dynamo-sglang SGLang image to v0.5.19-cu130 / 将 qwen3.5-fp4-gb300-dynamo-sglang 的 SGLang 镜像更新至 v0.5.19-cu130 #2909

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 qwen3.5-fp4-gb300-dynamo-sglang SGLang image to v0.5.19-cu130 / 将 qwen3.5-fp4-gb300-dynamo-sglang 的 SGLang 镜像更新至 v0.5.19-cu130 #2909

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
ebde675
perf(qwen3.5): bump GB300 FP4 dynamo-sglang image to v0.5.19-cu130
Klaud-Cold Sep 9, 2026
30fbdb6
fix(qwen3.5): pin Dynamo 1.5.0.dev20260908 for sglang v0.5.19 on GB300
Klaud-Cold Sep 9, 2026
278090e
chore(changelog): record Qwen3.5 FP4 GB300 dynamo-sglang v0.5.19 refresh
Klaud-Cold Sep 9, 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
2 changes: 1 addition & 1 deletion ...ti_node/srt-slurm-recipes/sglang/qwen3.5/gb300-fp4/8k1k/disagg/stp/8k1k_stp_lowlat_0.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -14,7 +14,7 @@ model:
precision: "fp4"

dynamo:
version: "1.1.0"
version: "1.5.0.dev20260908"

frontend:
type: dynamo
Expand Down
2 changes: 1 addition & 1 deletion ...ti_node/srt-slurm-recipes/sglang/qwen3.5/gb300-fp4/8k1k/disagg/stp/8k1k_stp_maxtpt_0.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ model:
precision: "fp4"

dynamo:
version: "1.1.0"
version: "1.5.0.dev20260908"

frontend:
type: dynamo
Expand Down
2 changes: 1 addition & 1 deletion ...ti_node/srt-slurm-recipes/sglang/qwen3.5/gb300-fp4/8k1k/disagg/stp/8k1k_stp_maxtpt_1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ model:
precision: "fp4"

dynamo:
version: "1.1.0"
version: "1.5.0.dev20260908"

frontend:
type: dynamo
Expand Down
2 changes: 1 addition & 1 deletion ...ti_node/srt-slurm-recipes/sglang/qwen3.5/gb300-fp4/8k1k/disagg/stp/8k1k_stp_maxtpt_2.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,7 +15,7 @@ model:
precision: "fp4"

dynamo:
version: "1.1.0"
version: "1.5.0.dev20260908"

frontend:
type: dynamo
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 @@ -6443,13 +6443,13 @@ qwen3.5-fp8-h100-sglang-mtp:

# ---------- 1k1k high-throughput (wide-EP TP=32 decode) ----------
qwen3.5-fp4-gb300-dynamo-sglang:
image: lmsysorg/sglang:v0.5.14-cu130
image: lmsysorg/sglang:v0.5.19-cu130
model: nvidia/Qwen3.5-397B-A17B-NVFP4-V2
model-prefix: qwen3.5
runner: gb300
precision: fp4
framework: dynamo-sglang
router: { name: dynamo-router, version: "1.1.0" }
router: { name: dynamo-router, version: "1.5.0.dev20260908" }
multinode: true
disagg: true
scenarios:
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 @@ -6969,3 +6969,11 @@
- "Use SGLang's current W4A4 MegaMoE and DP LM-head flags for DP-attention instead of the deprecated MegaMoE environment variables."
- "Resolve draft-model jobs through the existing B200 SGLang speculative recipe and the staged DeepSeek-V4-Pro-0813 checkpoint."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2821

- config-keys:
- qwen3.5-fp4-gb300-dynamo-sglang
description:
- "Bump the Qwen3.5 FP4 GB300 disaggregated Dynamo-SGLang image from lmsysorg/sglang:v0.5.14-cu130 to lmsysorg/sglang:v0.5.19-cu130."
- "Pin Dynamo 1.5.0.dev20260908 in the four 8k1k STP recipes (and the family's router metadata) because Dynamo 1.1.0 imports sglang.srt.server_args_config_parser, which sglang v0.5.19 moved to sglang.srt.utils.server_args_config_parser; no stable Dynamo release carries the compat shim yet."
- "Model, topology, concurrency lists, workloads and recipe references are unchanged."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2909
Loading