Skip to content

AMD][MI35X] Qwen3.5-fp8 SGLang mtp single-node benchmark #1671

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

Closed
1am9trash wants to merge 4 commits into from
+17 −8
Closed

AMD][MI35X] Qwen3.5-fp8 SGLang mtp single-node benchmark #1671

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
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
50efc8f
Remove non-mtp update
1am9trash 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
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 @@ -283,7 +283,7 @@ qwen3.5-fp8-mi355x-sglang:
- { tp: 4, ep: 1, conc-start: 32, 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 Down
16 changes: 9 additions & 7 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 @@ -18,21 +18,21 @@ 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
setup_eval_context
EVAL_CONTEXT_ARGS="--context-length $EVAL_MAX_MODEL_LEN"
else EVAL_CONTEXT_ARGS="--context-length $CONTEXT_LENGTH"
Copy link
Copy Markdown

@cursor cursor Bot Jun 5, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing throughput context length

High Severity

For normal benchmark runs (EVAL_ONLY not true), the server launch no longer receives --context-length. The script drops CONTEXT_LENGTH and the else branch that passed ISL + OSL + 20, so EVAL_CONTEXT_ARGS stays empty while throughput jobs still use fixed ISL/OSL from CI.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 50efc8f. Configure here.

fi
# Start GPU monitoring (power, temperature, clocks every second)
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 +41,13 @@ python3 -m sglang.launch_server \
--trust-remote-code \
--tokenizer-worker-num 6 \
--enable-aiter-allreduce-fusion \
--cuda-graph-max-bs $CONC \
--max-running-requests 512 \
--disable-radix-cache \
--max-prefill-tokens $MAX_PREFILL_TOKENS \
--chunked-prefill-size 32768 \
--scheduler-recv-interval 30 \
--mem-fraction-static 0.8 \
--mem-fraction-static 0.9 \
--model-loader-extra-config '{"enable_multithread_load": true}' \
--page-size 16 \
--speculative-algorithm EAGLE \
--speculative-num-steps 3 \
--speculative-eagle-topk 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 @@ -3474,3 +3474,10 @@
- "Use scheduler-recv-interval values 2/60/30/1200/600/1920 for conc 1-4/8/16/32/64/128-256"
- "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-mtp
description:
- "Bump image to lmsysorg/sglang-rocm:v0.5.12.post1-rocm720-mi35x-20260528."
- "Update script for aiter attention backend."
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/1671
Loading