Skip to content

[PowerX] collect Qwen3.5 FP8 B300 Dynamo-SGLang AgentX power / [PowerX] 采集 Qwen3.5 FP8 B300 Dynamo-SGLang AgentX 功耗 #4413

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
edwingao28 merged 10 commits into from
Nov 8, 2026
Merged

[PowerX] collect Qwen3.5 FP8 B300 Dynamo-SGLang AgentX power / [PowerX] 采集 Qwen3.5 FP8 B300 Dynamo-SGLang AgentX 功耗 #4413

Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
fcb8706
chore: update Qwen3.5 FP8 B300 SGLang to v0.5.22
edwingao28 Oct 23, 2026
66c3071
chore: start Qwen3.5 FP8 B300 SGLang TP4 at c1
edwingao28 Oct 23, 2026
75e1010
chore: repurpose for Qwen3.5 B300 AgentX power rerun
edwingao28 Nov 6, 2026
cffb6cd
chore: start Qwen3.5 FP8 B300 AgentX power sweep
edwingao28 Nov 6, 2026
dd940b6
chore: merge main for Qwen3.5 FP8 B300 power sweep
edwingao28 Nov 6, 2026
3c19aba
chore: sync with main
edwingao28 Nov 7, 2026
2faaa13
chore: sync with main
edwingao28 Nov 8, 2026
aebe4a4
chore: sync with main
edwingao28 Nov 8, 2026
5929098
chore: sync with main
edwingao28 Nov 8, 2026
520b15b
chore: sync with main
edwingao28 Nov 8, 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
7 changes: 7 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 @@ -12481,3 +12481,10 @@
- "Re-sweep Kimi-K3.1-Pro GB200 vLLM AgentX with the updated DSpark draft (Inferact/Kimi-K3.1-Pro-DSpark-preview @ 6a2ef20a) and the #4851 golden curve, so throughput forces AL 3.41 at 5 draft tokens and 3.19 at 4."
- "Set VLLM_HTTP_TIMEOUT_KEEP_ALIVE to 600 s on the aggregated server so AIPerf's reused session connections outlive uvicorn's 5 s idle timeout."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4864

- config-keys:
- qwen3.5-fp8-b300-dynamo-sglang-agentic-disagg
description:
- "Rerun the unchanged FP8 config to collect GPU power, because its published curve (2026-10-21) predates default-on multinode power collection and carries no valid power."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/4413
scenario-type: [agentic-coding]
Loading