Skip to content

[Qwen3.5 H200] extend FP8 SGLang 8k1k to c1-c128 / [Qwen3.5 H200] 将 FP8 SGLang 8k1k 并发扩展至 c1-c128 #4415

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

Open
edwingao28 wants to merge 2 commits into
base: main
Choose a base branch
from
Open

[Qwen3.5 H200] extend FP8 SGLang 8k1k to c1-c128 / [Qwen3.5 H200] 将 FP8 SGLang 8k1k 并发扩展至 c1-c128 #4415

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
48c2140
chore: extend Qwen3.5 FP8 H200 SGLang 8k1k to c1-c128
edwingao28 Oct 23, 2026
b7ad5ed
chore: set H200 changelog PR link
edwingao28 Oct 23, 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
4 changes: 2 additions & 2 deletions inferencex-e2e/benchmarks/single_node/srt-slurm-recipes/qwen3.5/sglang/h200-fp8/8k1k.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,7 +44,7 @@ zip_override_concurrency:
roles:
agg:
args:
cuda-graph-max-bs: [4, 8, 16, 32, 64]
cuda-graph-max-bs: [1, 2, 4, 8, 16, 32, 64, 128]
benchmark:
env:
CONC: ['4', '8', '16', '32', '64']
CONC: ['1', '2', '4', '8', '16', '32', '64', '128']
4 changes: 2 additions & 2 deletions inferencex-e2e/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1677,8 +1677,8 @@ qwen3.5-fp8-h200-sglang:
search-space:
- tp: 8
ep: 8
conc-start: 4
conc-end: 64
conc-start: 1
conc-end: 128
srt-recipe: 8k1k.yaml

qwen3.5-fp8-h200-sglang-mtp:
Expand Down
6 changes: 6 additions & 0 deletions inferencex-e2e/perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10871,3 +10871,9 @@
- "Update the vLLM ROCm image from v0.31.0 to v0.32.0."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4395
scenario-type: [agentic-coding]

- config-keys:
- qwen3.5-fp8-h200-sglang
description:
- "Extend TP8/EP8 8k1k concurrency from 4-64 to 1-128 (cuda-graph-max-bs follows concurrency)."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4415
Loading