Skip to content

[AMD/ROCM] atom glm5 fp8 on mi355x #1126

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
seungrokj wants to merge 5 commits into
base: main
Choose a base branch
from
+14 −1
Open

[AMD/ROCM] atom glm5 fp8 on mi355x #1126

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
d136db5
Update GLM5 FP8 atom config: new image, add TP=4, set gpu-memory-util…
seungrokj Apr 24, 2026
8a1620c
Fix perf-changelog entry for GLM5 FP8 atom config
seungrokj Apr 24, 2026
66c42b4
Add PR link to perf-changelog for GLM5 FP8 atom config
seungrokj Apr 24, 2026
2b41edd
Merge branch 'main' into srok/atom_glm5_fp8
seungrokj Apr 25, 2026
68ce144
Merge branch 'main' into srok/atom_glm5_fp8
seungrokj Apr 27, 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: 3 additions & 1 deletion .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -362,7 +362,7 @@ glm5-fp8-mi355x-sglang-mtp:
- { tp: 8, conc-start: 4, conc-end: 64, spec-decoding: mtp }

glm5-fp8-mi355x-atom:
image: rocm/atom:rocm7.2.1-ubuntu24.04-pytorch2.9.1-atom0.1.2.post
image: rocm/atom:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.2.post
model: zai-org/GLM-5-FP8
model-prefix: glm5
runner: mi355x
Expand All @@ -373,10 +373,12 @@ glm5-fp8-mi355x-atom:
- isl: 1024
osl: 1024
search-space:
- { tp: 4, conc-start: 4, conc-end: 256 }
- { tp: 8, conc-start: 4, conc-end: 256 }
- isl: 8192
osl: 1024
search-space:
- { tp: 4, conc-start: 4, conc-end: 256 }
- { tp: 8, conc-start: 4, conc-end: 256 }

glm5.1-fp4-mi355x-sglang:
Expand Down
2 changes: 2 additions & 0 deletions benchmarks/single_node/glm5_fp8_mi355x_atom.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -39,6 +39,7 @@ fi

# Start GPU monitoring (power, temperature, clocks every second)
start_gpu_monitor
MEM_FRAC_STATIC=0.9

set -x
pip install -U transformers
Expand All @@ -47,6 +48,7 @@ python3 -m atom.entrypoints.openai_server \
--server-port $PORT \
-tp $TP \
--kv_cache_dtype fp8 $CALCULATED_MAX_MODEL_LEN $EP \
--gpu-memory-utilization $MEM_FRAC_STATIC \
--default-chat-template-kwargs '{"enable_thinking": false}' \
--trust-remote-code \
> $SERVER_LOG 2>&1 &
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 @@ -1757,6 +1757,15 @@
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1129


- config-keys:
- glm5-fp8-mi355x-atom
description:
- "Update GLM-5 FP8 MI355X ATOM benchmark: new image, add TP=4, set gpu-memory-utilization"
- "Image: rocm/atom:rocm7.2.2_ubuntu24.04_py3.12_pytorch_release_2.10.0_atom0.1.2.post"
- "Add TP=4, concurrency 4-256 for 1k1k and 8k1k sequence lengths"
- "Add --gpu-memory-utilization 0.9 to server launch"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1126

- config-keys:
- dsv4-fp8-h200-vllm
description:
Expand Down
Loading