Skip to content

perf(qwen3.5-fp4-b200-sglang-mtp): add TEP2 arm on NVFP4-V2 / perf(qwen3.5-fp4-b200-sglang-mtp): 基于 NVFP4-V2 添加 TEP2 组合 #2550

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

Merged
Ankur-singh merged 10 commits into from
Aug 13, 2026
+10 −0
Merged

perf(qwen3.5-fp4-b200-sglang-mtp): add TEP2 arm on NVFP4-V2 / perf(qwen3.5-fp4-b200-sglang-mtp): 基于 NVFP4-V2 添加 TEP2 组合 #2550

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
18d87ef
perf(qwen3.5-fp4-b200-sglang-mtp): add TEP2 arm
hshrivastava-droid Aug 10, 2026
e364399
Update perf-changelog pr-link for #2550
hshrivastava-droid Aug 10, 2026
743f1ab
Merge remote-tracking branch 'origin/main' into pr-2550-reuse-10261
Ankur-singh Aug 11, 2026
b927d03
Merge remote-tracking branch 'origin/main' into pr-2550-reuse-19695
Ankur-singh Aug 11, 2026
4a7b627
Merge remote-tracking branch 'origin/main' into pr2550
Ankur-singh Aug 12, 2026
f6c282c
chore(changelog): trim TEP2 entry description to two bullets
hshrivastava-droid Aug 12, 2026
6a93213
Merge origin/main and resolve perf-changelog
hshrivastava-droid Aug 12, 2026
5094a86
Merge origin/qwen3.5-fp4-b200-sglang-mtp-tep2 and keep two-bullet des…
hshrivastava-droid Aug 12, 2026
21d6bbb
Merge branch 'main' into qwen3.5-fp4-b200-sglang-mtp-tep2
hshrivastava-droid Aug 12, 2026
f705dd1
Merge remote-tracking branch 'origin/main' into pr-2550-reuse-74874
Ankur-singh Aug 13, 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
1 change: 1 addition & 0 deletions configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1246,6 +1246,7 @@ qwen3.5-fp4-b200-sglang-mtp:
search-space:
- { tp: 4, ep: 1, conc-start: 4, conc-end: 4, spec-decoding: mtp }
- { tp: 2, ep: 1, conc-start: 4, conc-end: 64, spec-decoding: mtp }
- { tp: 2, ep: 2, conc-list: [16, 32, 64], spec-decoding: mtp }

qwen3.5-fp8-b200-sglang-mtp:
image: lmsysorg/sglang:v0.5.14-cu130
Expand Down
9 changes: 9 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5909,3 +5909,12 @@
- "Increase MTP speculative steps from 3 to 5 (num-draft-tokens 4→6) and raise SGLANG_SIMULATE_ACC_LEN from 2.99 to 3.61 to reflect higher measured acceptance rate, targeting ~15% throughput improvement"
- "Replace the TP8/EP8 low-concurrency arm (conc [1,2,4]) hicache offload with kv-offloading: none to reduce per-request latency at low load; conc [1,2,4] are now tested on both tp=4+hicache and tp=8+no-offload so SemiAnalysis can select the Pareto-optimal point per concurrency"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2570

- config-keys:
- qwen3.5-fp4-b200-sglang-mtp
scenario-type:
- fixed-seq-len
description:
- "Add a TEP2 arm (tp 2, ep 2) to the qwen3.5-fp4-b200-sglang-mtp 8k/1k sweep at concurrency 16, 32, and 64"
- "Rides on the NVFP4-V2 checkpoint switch from #2205"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2550