Skip to content

[AMD][MI35X] Qwen3.5-fp4 SGLang single-node benchmark env update #1716

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
yichiche wants to merge 4 commits into
base: main
Choose a base branch
from
+12 −2
Open

[AMD][MI35X] Qwen3.5-fp4 SGLang single-node benchmark env update #1716

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
08427ba
[AMD] qwen3.5-mxfp4-mi355x: bump image to v0.5.13 and enable AITER_FL…
yichiche Jun 12, 2026
b126701
[AMD] qwen3.5-mxfp4-mi355x-mtp: add AITER_FLYDSL_FORCE=1 to MTP bench…
yichiche Jun 12, 2026
56da307
[AMD] perf-changelog: add qwen3.5-mxfp4-mi355x v0.5.13 image bump entry
yichiche Jun 12, 2026
9d78e2f
[Fix] perf-changelog: add missing pr-link for qwen3.5-mxfp4-mi355x entry
yichiche Jun 12, 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 .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -427,7 +427,7 @@ qwen3.5-fp8-mi355x-sglang-disagg:
- "DECODE_MTP_SIZE=0"

qwen3.5-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604
image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down Expand Up @@ -469,7 +469,7 @@ qwen3.5-fp4-mi355x-atom:
- { tp: 4, conc-start: 4, conc-end: 16 }

qwen3.5-fp4-mi355x-sglang-mtp:
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604
image: lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612
Comment thread
yichiche marked this conversation as resolved.
model: amd/Qwen3.5-397B-A17B-MXFP4
model-prefix: qwen3.5
runner: mi355x
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi

export SGLANG_USE_AITER=1
export SGLANG_USE_AITER_UNIFIED_ATTN=1
export AITER_FLYDSL_FORCE=1

SERVER_LOG=/workspace/server.log
MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/fixed_seq_len/qwen3.5_fp4_mi355x_mtp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -19,6 +19,7 @@ hf download "$MODEL"

export SGLANG_USE_AITER=1
export SGLANG_USE_AITER_UNIFIED_ATTN=1
export AITER_FLYDSL_FORCE=1

SERVER_LOG=/workspace/server.log
MEM_FRAC_STATIC=${MEM_FRAC_STATIC:-0.8}
Expand Down
8 changes: 8 additions & 0 deletions perf-changelog.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3600,3 +3600,11 @@
- "MI355x DSR1-FP4: Include TP4 configurations for 8k1k"
- "Expand the TP sweep (included TP=4) for 8k/1k configuration for conc=4 to 64"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1692

- config-keys:
- qwen3.5-fp4-mi355x-sglang
- qwen3.5-fp4-mi355x-sglang-mtp
description:
- "Bump image from lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260604 to lmsysorg/sglang-rocm:v0.5.13-rocm720-mi35x-20260612"
- "Enable AITER_FLYDSL_FORCE=1 in both non-MTP and MTP benchmark scripts"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1716