Skip to content

glm5.1-fp4-mi355x-sglang: bump image to v0.5.13.post1-20260622 + enable aiter allreduce fusion #1905

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
jiacao-amd wants to merge 3 commits into
base: main
Choose a base branch
from
+9 −1
Open

glm5.1-fp4-mi355x-sglang: bump image to v0.5.13.post1-20260622 + enable aiter allreduce fusion #1905

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
65a9952
glm5.1-fp4-mi355x-sglang: bump image to v0.5.13.post1-20260622 + enab…
jiacao-amd Jun 23, 2026
40ba903
Update the perf-changelog
chunfangamd Jun 24, 2026
20a2114
Merge branch 'main' into glm5.1-fp4-mi355x-image-bump-arfusion
chunfangamd Jun 24, 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 .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -679,7 +679,7 @@ glm5-fp8-mi355x-atom:
- { tp: 8, conc-start: 4, conc-end: 256 }

glm5.1-fp4-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260529
image: lmsysorg/sglang-rocm:v0.5.13.post1-rocm720-mi35x-20260622
model: amd/GLM-5.1-MXFP4
model-prefix: glm5.1
runner: mi355x
Expand Down
1 change: 1 addition & 0 deletions benchmarks/single_node/fixed_seq_len/glm5.1_fp4_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -52,6 +52,7 @@ python3 -m sglang.launch_server \
--nsa-decode-backend tilelang $EVAL_CONTEXT_ARGS \
--kv-cache-dtype fp8_e4m3 \
--tokenizer-worker-num $((TP*2)) \
--enable-aiter-allreduce-fusion \
--disable-radix-cache> $SERVER_LOG 2>&1 &

SERVER_PID=$!
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 @@ -4041,6 +4041,13 @@
- "No benchmark configuration change; reuse the exact 25-point fixed-sequence matrix and 2 eval jobs"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1869

- config-keys:
- glm5.1-fp4-mi355x-sglang
description:
- "Bump SGLang ROCm image from v0.5.12.post1-rocm720-mi35x-20260529 to v0.5.13.post1-rocm720-mi35x-20260622"
- "Enable aiter allreduce fusion via --enable-aiter-allreduce-fusion in benchmarks/single_node/fixed_seq_len/glm5.1_fp4_mi355x.sh"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1905

- config-keys:
- minimaxm3-fp8-b300-dynamo-vllm
description:
Expand Down