Skip to content

[AMD][MI35X] Sweep TP2/EP1 instead of TP2/EP2 on the Qwen3.5 MXFP4 MI355X AgentX arm #2694

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
yichiche wants to merge 2 commits into from
+10 −1
Closed

[AMD][MI35X] Sweep TP2/EP1 instead of TP2/EP2 on the Qwen3.5 MXFP4 MI355X AgentX arm #2694

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
b390e95
[AMD][MI35X] Sweep TP2/EP1 instead of TP2/EP2 on the Qwen3.5 MXFP4 MI…
yichiche Aug 20, 2026
5c9797c
[AMD][MI35X] Point the Qwen3.5 AgentX TP2/EP1 changelog entry to PR #…
yichiche Aug 20, 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 configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -372,7 +372,7 @@ qwen3.5-fp4-mi355x-sglang-agentic-mtp:
agentic-coding:
- dram-utilization: 0.80
search-space:
- { tp: 2, ep: 2, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20] }
- { tp: 2, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20, 24, 28, 32] }
- { tp: 4, ep: 1, spec-decoding: mtp, kv-offloading: none, conc-list: [1, 4, 8, 12, 16, 20, 24, 28, 32, 40] }

qwen3.5-fp4-mi355x-sglang-disagg:
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 @@ -6251,3 +6251,12 @@
description:
- "Refresh with lower stream interval to collect correct client metrics"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2686

- config-keys:
- qwen3.5-fp4-mi355x-sglang-agentic-mtp
scenario-type:
- agentic-coding
description:
- "Replace the TP2/EP2 arm with TP2/EP1 so the 2-GPU point matches qwen3.5-fp4-b200-sglang-agentic-mtp."
- "Extend the TP2 concurrency list to 1, 4, 8, 12, 16, 20, 24, 28, and 32."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2694
Comment thread
yichiche marked this conversation as resolved.
Loading