Skip to content

[DRAFT] [AMD] Update Minimax M2.5 MI325 image and adjust search space #953

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
benenzhu wants to merge 9 commits into
base: main
Choose a base branch
from
+19 −5
Open

[DRAFT] [AMD] Update Minimax M2.5 MI325 image and adjust search space #953

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
9 commits
Select commit Hold shift + click to select a range
0c649bb
add minimax mi325
benenzhu Mar 27, 2026
c49fa9d
update minimax mi300x/mi325x perf-changelog pr-link
benenzhu Mar 27, 2026
19c735a
only minimax mi325
benenzhu Mar 27, 2026
f05ab17
fix
benenzhu Mar 27, 2026
18aa860
Merge branch 'main' into amd/zhu/minimax
benenzhu Mar 27, 2026
aebc624
fix
benenzhu Mar 27, 2026
b0b54d7
remove mi300x configs
benenzhu Mar 27, 2026
ffca5ae
Merge branch 'main' into amd/zhu/minimax
benenzhu Mar 27, 2026
4f857de
Merge branch 'main' into amd/zhu/minimax
functionstackx Mar 28, 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
8 changes: 4 additions & 4 deletions .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -417,7 +417,7 @@ minimaxm2.5-fp8-mi300x-vllm:
- { tp: 4, conc-start: 4, conc-end: 64 }

minimaxm2.5-fp8-mi325x-vllm:
image: vllm/vllm-openai-rocm:v0.16.0
image: vllm/vllm-openai-rocm:v0.18.0
model: MiniMaxAI/MiniMax-M2.5
model-prefix: minimaxm2.5
runner: mi325x
Expand All @@ -429,17 +429,17 @@ minimaxm2.5-fp8-mi325x-vllm:
osl: 1024
search-space:
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 512 }
- isl: 1024
osl: 8192
search-space:
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 256 }
- isl: 8192
osl: 1024
search-space:
- { tp: 2, conc-start: 4, conc-end: 64 }
- { tp: 4, conc-start: 4, conc-end: 64 }
- { tp: 8, ep: 8, conc-start: 4, conc-end: 256 }

gptoss-fp4-mi300x-vllm:
image: vllm/vllm-openai-rocm:v0.17.0
Expand Down
9 changes: 8 additions & 1 deletion benchmarks/single_node/minimaxm2.5_fp8_mi325x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,6 +5,7 @@ source "$(dirname "$0")/../benchmark_lib.sh"
check_env_vars \
MODEL \
TP \
EP_SIZE \
CONC \
ISL \
OSL \
Expand All @@ -30,16 +31,22 @@ export VLLM_ROCM_USE_AITER=1
SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}

if [ "$EP_SIZE" -gt 1 ]; then
EP=" --enable-expert-parallel"
else
EP=" "
fi

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

set -x
vllm serve $MODEL --port $PORT \
--tensor-parallel-size=$TP \
$EP \
--gpu-memory-utilization 0.95 \
--max-model-len $MAX_MODEL_LEN \
--block-size=32 \
--disable-log-requests \
--no-enable-prefix-caching \
--trust-remote-code > $SERVER_LOG 2>&1 &

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 @@ -1074,6 +1074,13 @@
- "dsr1-fp8-b200-sglang-mtp: v0.5.8-cu130-amd64 → v0.5.9-cu130"
- "dsr1-fp8-h200-sglang: v0.5.9-cu129-amd64 → v0.5.9-cu130"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/943

- config-keys:
- minimaxm2.5-fp8-mi325x-vllm
description:
- "Upgrade vLLM ROCm image from v0.16.0 to v0.18.0"
- "Replace TP4 with TP8/EP8, add conc range 4-256"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/953

- config-keys:
- kimik2.5-fp4-mi355x-vllm
Expand Down