Skip to content

chore: update vllm to 11.0 and make changes from PR 102 #159

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
functionstackx merged 1 commit into from
Nov 4, 2025
Merged

chore: update vllm to 11.0 and make changes from PR 102 #159

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
6 changes: 3 additions & 3 deletions .github/configs/nvidia-master.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -198,7 +198,7 @@ gptoss-fp4-b200-trt:
- { tp: 8, conc-start: 4, conc-end: 8 }

gptoss-fp4-b200-vllm:
image: vllm/vllm-openai:v0.10.2
image: vllm/vllm-openai:v0.11.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: b200
Expand Down Expand Up @@ -228,7 +228,7 @@ gptoss-fp4-b200-vllm:
- { tp: 8, conc-start: 4, conc-end: 4 }

gptoss-fp4-h100-vllm:
image: vllm/vllm-openai:v0.10.2
image: vllm/vllm-openai:v0.11.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: h100
Expand Down Expand Up @@ -286,7 +286,7 @@ gptoss-fp4-h200-trt:
- { tp: 8, ep: 8, dp-attn: false, conc-start: 4, conc-end: 8 }

gptoss-fp4-h200-vllm:
image: vllm/vllm-openai:v0.10.2
image: vllm/vllm-openai:v0.11.0
model: openai/gpt-oss-120b
model-prefix: gptoss
runner: h200
Expand Down
3 changes: 2 additions & 1 deletion benchmarks/gptoss_fp4_h100_docker.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,6 +9,7 @@
# CONC

cat > config.yaml << EOF
compilation-config: '{"cudagraph_mode":"PIECEWISE"}'
async-scheduling: true
no-enable-prefix-caching: true
cuda-graph-sizes: 2048
Expand All @@ -20,7 +21,7 @@ export PYTHONNOUSERSITE=1

set -x
vllm serve $MODEL --host=0.0.0.0 --port=$PORT \
--config=config.yaml \
--config config.yaml \
--gpu-memory-utilization=0.9 \
--tensor-parallel-size=$TP \
--max-num-seqs=$CONC \
Expand Down
3 changes: 2 additions & 1 deletion benchmarks/gptoss_fp4_h100_slurm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,7 @@
echo "JOB $SLURM_JOB_ID running on $SLURMD_NODENAME"

cat > config.yaml << EOF
compilation-config: '{"cudagraph_mode":"PIECEWISE"}'
async-scheduling: true
no-enable-prefix-caching: true
cuda-graph-sizes: 2048
Expand All @@ -29,7 +30,7 @@ export TORCH_CUDA_ARCH_LIST="9.0"

set -x
PYTHONNOUSERSITE=1 vllm serve $MODEL --host=0.0.0.0 --port=$PORT \
--config=config.yaml \
--config config.yaml \
--gpu-memory-utilization=0.9 \
--tensor-parallel-size=$TP \
--max-num-seqs=$CONC \
Expand Down
1 change: 1 addition & 0 deletions benchmarks/gptoss_fp4_h200_slurm.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -31,6 +31,7 @@ fi

# Create config.yaml
cat > config.yaml << EOF
compilation-config: '{"cudagraph_mode":"PIECEWISE"}'
async-scheduling: true
no-enable-prefix-caching: true
cuda-graph-sizes: 2048
Expand Down