Skip to content

[Do not merge][AMD]Update cli args for qwen3.5 #980

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
zhentaocc wants to merge 10 commits into
base: main
Choose a base branch
from
+44 −8
Open

[Do not merge][AMD]Update cli args for qwen3.5 #980

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
10 commits
Select commit Hold shift + click to select a range
9f21af1
feat: enhance Qwen benchmark scripts with additional parameters
Mar 31, 2026
44bc53a
Update perf-changelog.yaml to include new Qwen3.5 FP8 and BF16 SGLang…
Mar 31, 2026
128ddfd
Update SGLang image versions for Qwen3.5 configurations in amd-master…
Mar 31, 2026
ab7166e
use 0327 build
Mar 31, 2026
036a487
Update perf-changelog.yaml to reflect the new PR link for Qwen3.5 FP8…
Mar 31, 2026
5077256
Update Qwen3.5 image tags in amd-master.yaml to v0.5.10rc0 for MI355X…
Mar 31, 2026
46e763f
Update Qwen3.5 FP8 and BF16 SGLang benchmark descriptions in perf-cha…
Mar 31, 2026
bf316da
Enhance Qwen3.5 benchmark scripts for MI355X by adding EP_SIZE parame…
Mar 31, 2026
251c54e
Update search-space configurations in amd-master.yaml for Qwen3.5 ben…
Mar 31, 2026
6fe8422
Remove context length parameter from Qwen3.5 BF16 and FP8 benchmark s…
Mar 31, 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
12 changes: 8 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 @@ -114,7 +114,7 @@ dsr1-fp8-mi355x-sglang:
- { tp: 8, conc-start: 4, conc-end: 64 }

qwen3.5-bf16-mi355x-sglang:
image: rocm/sgl-dev:v0.5.8.post1-rocm720-mi35x-20260215
image: lmsysorg/sglang-rocm:v0.5.10rc0-rocm720-mi35x-20260327
model: Qwen/Qwen3.5-397B-A17B
model-prefix: qwen3.5
runner: mi355x
Expand All @@ -125,11 +125,13 @@ qwen3.5-bf16-mi355x-sglang:
- isl: 1024
osl: 1024
search-space:
- { tp: 8, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 256 }
- { tp: 8, ep: 8, conc-start: 64, conc-end: 256 }
- isl: 8192
osl: 1024
search-space:
- { tp: 8, conc-start: 4, conc-end: 64 }
- { tp: 8, conc-start: 4, conc-end: 256 }
- { tp: 8, ep: 8, conc-start: 64, conc-end: 256 }

qwen3.5-bf16-mi300x-sglang:
image: lmsysorg/sglang:v0.5.9-rocm720-mi30x
Expand Down Expand Up @@ -186,7 +188,7 @@ qwen3.5-fp8-mi325x-sglang:
- { tp: 8, conc-start: 4, conc-end: 64 }

qwen3.5-fp8-mi355x-sglang:
image: rocm/sgl-dev:v0.5.8.post1-rocm720-mi35x-20260218
image: lmsysorg/sglang-rocm:v0.5.10rc0-rocm720-mi35x-20260327
model: Qwen/Qwen3.5-397B-A17B-FP8
model-prefix: qwen3.5
runner: mi355x
Expand All @@ -198,10 +200,12 @@ qwen3.5-fp8-mi355x-sglang:
osl: 1024
search-space:
- { tp: 8, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 16, conc-end: 256 }
- isl: 8192
osl: 1024
search-space:
- { tp: 8, conc-start: 4, conc-end: 64 }
- { tp: 4, ep: 4, conc-start: 16, conc-end: 256 }

qwen3.5-fp8-mi300x-sglang:
image: lmsysorg/sglang:v0.5.9-rocm720-mi30x
Expand Down
16 changes: 14 additions & 2 deletions benchmarks/single_node/qwen3.5_bf16_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ check_env_vars \
ISL \
OSL \
RANDOM_RANGE_RATIO \
RESULT_FILENAME
RESULT_FILENAME \
EP_SIZE

if [[ -n "$SLURM_JOB_ID" ]]; then
echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
Expand All @@ -19,11 +20,14 @@ hf download "$MODEL"

SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}
CONTEXT_LENGTH=$((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"
fi
# Start GPU monitoring (power, temperature, clocks every second)
start_gpu_monitor
Expand All @@ -34,8 +38,16 @@ python3 -m sglang.launch_server \
--host=0.0.0.0 \
--port $PORT \
--tensor-parallel-size $TP \
--ep-size $EP_SIZE \
--data-parallel-size 1 \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--tokenizer-worker-num 6 \
--enable-aiter-allreduce-fusion \
--cuda-graph-max-bs $CONC \
--disable-radix-cache \
--max-prefill-tokens $MAX_PREFILL_TOKENS \
--scheduler-recv-interval 30 \
--mem-fraction-static 0.75 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

Expand Down
16 changes: 14 additions & 2 deletions benchmarks/single_node/qwen3.5_fp8_mi355x.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,7 +9,8 @@ check_env_vars \
ISL \
OSL \
RANDOM_RANGE_RATIO \
RESULT_FILENAME
RESULT_FILENAME \
EP_SIZE

if [[ -n "$SLURM_JOB_ID" ]]; then
echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"
Expand All @@ -19,11 +20,14 @@ hf download "$MODEL"

SERVER_LOG=/workspace/server.log
PORT=${PORT:-8888}
CONTEXT_LENGTH=$((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"
fi
# Start GPU monitoring (power, temperature, clocks every second)
start_gpu_monitor
Expand All @@ -34,8 +38,16 @@ python3 -m sglang.launch_server \
--host=0.0.0.0 \
--port $PORT \
--tensor-parallel-size $TP \
--ep-size $EP_SIZE \
--data-parallel-size 1 \
--trust-remote-code \
--mem-fraction-static 0.8 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &
--tokenizer-worker-num 6 \
--enable-aiter-allreduce-fusion \
--cuda-graph-max-bs $CONC \
--disable-radix-cache \
--max-prefill-tokens $MAX_PREFILL_TOKENS \
--scheduler-recv-interval 30 \
--mem-fraction-static 0.75 $EVAL_CONTEXT_ARGS > $SERVER_LOG 2>&1 &

SERVER_PID=$!

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 @@ -1220,3 +1220,11 @@
- "Uses nvidia/GLM-5-NVFP4 model with modelopt_fp4 quantization"
- "Image: lmsysorg/sglang:nightly-dev-cu13-20260328-a27651d5"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/973
- config-keys:
- qwen3.5-bf16-mi355x-sglang
- qwen3.5-fp8-mi355x-sglang
description:
- "Update cli args of Qwen3.5 FP8 and BF16 SGLang benchmarks for MI355X to achieve better performance"
- "Use lmsysorg/sglang-rocm:v0.5.10rc0-rocm720-mi35x-20260327"
pr-link: https://github.com/SemiAnalysisAI/InferenceX/pull/980

Loading