Skip to content

[AMD] update model in case qwen3.5-fp4-mi355x-sglang #2465

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
yuzho-amd wants to merge 3 commits into from
+8 −1
Closed

[AMD] update model in case qwen3.5-fp4-mi355x-sglang #2465

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
c26b731
update qwen3.5-397b-mxfp4 model
yuzho-amd Aug 3, 2026
b3fb4e3
update PR
yuzho-amd Aug 3, 2026
a05e1e4
chore: sync PR 2465 with upstream main
yuzho-amd Aug 11, 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 @@ -307,7 +307,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:

qwen3.5-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.16-rocm720-mi35x-20260730
model: amd/Qwen3.5-397B-A17B-MXFP4
model: amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2
model-prefix: qwen3.5
runner: mi355x
precision: fp4
Expand Down
7 changes: 7 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5770,3 +5770,10 @@
- "models.yaml: add mtp_flags (--speculative-algorithm EAGLE --speculative-eagle-topk 1) to DeepSeek-V4-Pro-AgentX; num-steps/num-draft-tokens are derived from DECODE_MTP_SIZE in server_sglang.sh. DeepSeek-V4's MTP head is a native NextN/EAGLE draft shipped with the model, so no --speculative-draft-model-path is needed."
- "Two search-space arms: TP8/EP1 no-DP at conc-list [2,4,8,16,32], and TP8/EP8/DPA (ep=8, dp-attn=true) at conc-list [64,96,128], both on image lmsysorg/sglang-rocm:v0.5.15.post1-rocm720-mi35x-20260719."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2309

- config-keys:
- qwen3.5-fp4-mi355x-sglang
description:
- "Update the Qwen3.5 FP4 MI355X SGLang checkpoint to amd/Qwen3.5-397B-A17B-MXFP4-AttnFP8-V2"
- "Quantize attention to PTPC FP8 and shared experts to MXFP4"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/2465