Skip to content

[AMD][MI35X] Qwen3.5-fp8 SGLang single-node benchmark #1669

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

Merged
chunfangamd merged 11 commits into from
Jun 5, 2026
+31 −19
Merged

[AMD][MI35X] Qwen3.5-fp8 SGLang single-node benchmark #1669

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
11 commits
Select commit Hold shift + click to select a range
b28da84
[AMD] Switch Qwen3.5 FP8 MI355X benchmarks to aiter attention backend
yichiche Jun 5, 2026
3b685b4
[AMD] Bump Qwen3.5 FP8 MI355X image to v0.5.12.post1-rocm720-mi35x-20…
yichiche Jun 5, 2026
a7b115d
Update change log
1am9trash Jun 5, 2026
f5fa87e
Change mem-fraction-static back to 0.8
1am9trash Jun 5, 2026
13c80c7
Merge remote-tracking branch 'origin/main' into amd/qwen3.5-fp8
1am9trash Jun 5, 2026
373204f
Add context len args and limit batch to CONC size
1am9trash Jun 5, 2026
2021e7c
Fix typo
1am9trash Jun 5, 2026
97ca3c1
Fix typo
1am9trash Jun 5, 2026
fe3633a
Change config to tp4
1am9trash Jun 5, 2026
536fd20
cleanup
Oseltamivir Jun 5, 2026
930b1f8
Merge branch 'main' into amd/qwen3.5-fp8
Oseltamivir Jun 5, 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
18 changes: 6 additions & 12 deletions .github/configs/amd-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -261,7 +261,7 @@ qwen3.5-fp8-mi325x-sglang:
- { tp: 8, conc-start: 4, conc-end: 64 }

qwen3.5-fp8-mi355x-sglang:
image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260517
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260528
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: mi355x
Expand All @@ -273,17 +273,14 @@ qwen3.5-fp8-mi355x-sglang:
- isl: 1024
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 32 }
- { tp: 8, ep: 8, conc-start: 64, conc-end: 256 }
- { tp: 2, ep: 2, conc-start: 128, conc-end: 256 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 256 }
- isl: 8192
osl: 1024
search-space:
- { tp: 2, ep: 2, conc-start: 4, conc-end: 32 }
- { tp: 4, ep: 1, conc-start: 32, conc-end: 256 }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 256 }

qwen3.5-fp8-mi355x-sglang-mtp:
image: lmsysorg/sglang-rocm:v0.5.12-rocm720-mi35x-20260517
image: lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260528
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: mi355x
Expand All @@ -295,14 +292,11 @@ qwen3.5-fp8-mi355x-sglang-mtp:
- isl: 1024
osl: 1024
search-space:
- { tp: 8, ep: 1, conc-start: 4, conc-end: 32, spec-decoding: mtp }
- { tp: 8, ep: 8, conc-start: 64, conc-end: 256, spec-decoding: mtp }
- { tp: 2, ep: 2, conc-start: 128, conc-end: 256, spec-decoding: mtp }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp }
- isl: 8192
osl: 1024
search-space:
- { tp: 2, ep: 2, conc-start: 4, conc-end: 32, spec-decoding: mtp }
- { tp: 4, ep: 1, conc-start: 32, conc-end: 256, spec-decoding: mtp }
- { tp: 4, ep: 1, conc-start: 4, conc-end: 256, spec-decoding: mtp }

# Diverged from qwen3.5-fp8-mi355x-sglang (agentic-coding sibling). Metadata is
# identical to origin/main's qwen3.5-fp8-mi355x-sglang; the split exists because this
Expand Down
13 changes: 9 additions & 4 deletions benchmarks/single_node/fixed_seq_len/qwen3.5_fp8_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,11 @@ fi

if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi

export SGLANG_USE_AITER_UNIFIED_ATTN=1
export SGLANG_USE_AITER=1

SERVER_LOG=/workspace/server.log
CONTEXT_LENGTH=$((ISL + OSL + 20))
MAX_PREFILL_TOKENS=32768

EVAL_CONTEXT_ARGS=""
if [ "${EVAL_ONLY}" = "true" ]; then
Expand All @@ -32,7 +34,7 @@ fi
start_gpu_monitor

python3 -m sglang.launch_server \
--attention-backend triton \
--attention-backend aiter \
--model-path $MODEL \
--host=0.0.0.0 \
--port $PORT \
Expand All @@ -41,11 +43,14 @@ python3 -m sglang.launch_server \
--trust-remote-code \
--tokenizer-worker-num 6 \
--enable-aiter-allreduce-fusion \
--max-running-requests $CONC \
--cuda-graph-max-bs $CONC \
--disable-radix-cache \
--max-prefill-tokens $MAX_PREFILL_TOKENS \
--chunked-prefill-size 32768 \
--scheduler-recv-interval 30 \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--mem-fraction-static 0.8 \
--model-loader-extra-config '{"enable_multithread_load": true}' \
--page-size 16 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
Comment thread
1am9trash marked this conversation as resolved.

SERVER_PID=$!

Expand Down
11 changes: 8 additions & 3 deletions benchmarks/single_node/fixed_seq_len/qwen3.5_fp8_mi355x_mtp.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -18,9 +18,11 @@ fi

if [[ "$MODEL" != /* ]]; then hf download "$MODEL"; fi

export SGLANG_USE_AITER_UNIFIED_ATTN=1
export SGLANG_USE_AITER=1

SERVER_LOG=/workspace/server.log
CONTEXT_LENGTH=$((ISL + OSL + 20))
MAX_PREFILL_TOKENS=32768

EVAL_CONTEXT_ARGS=""
if [ "${EVAL_ONLY}" = "true" ]; then
Expand All @@ -32,7 +34,7 @@ fi
start_gpu_monitor

python3 -m sglang.launch_server \
--attention-backend triton \
--attention-backend aiter \
--model-path $MODEL \
--host=0.0.0.0 \
--port $PORT \
Expand All @@ -41,11 +43,14 @@ python3 -m sglang.launch_server \
--trust-remote-code \
--tokenizer-worker-num 6 \
--enable-aiter-allreduce-fusion \
--max-running-requests $CONC \
--cuda-graph-max-bs $CONC \
--disable-radix-cache \
--max-prefill-tokens $MAX_PREFILL_TOKENS \
--chunked-prefill-size 32768 \
--scheduler-recv-interval 30 \
--mem-fraction-static 0.8 \
--model-loader-extra-config '{"enable_multithread_load": true}' \
--page-size 16 \
--speculative-algorithm EAGLE \
--speculative-num-steps 3 \
--speculative-eagle-topk 1 \
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 @@ -3481,6 +3481,14 @@
- "Set max-running-requests=256, chunked-prefill-size=16384, mem-fraction-static=0.8, cuda-graph-max-bs=CONC, and enable symm-mem"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1544

- config-keys:
- qwen3.5-fp8-mi355x-sglang
- qwen3.5-fp8-mi355x-sglang-mtp
description:
- "Bump image to lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260528."
- "Update script for aiter attention backend from triton."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1669

- config-keys:
- minimaxm2.5-fp8-h200-vllm
description:
Expand Down
Loading