Skip to content

chore: update aggregated examples for vllm xpu 0.24.0 #11229

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
rmccorm4 merged 6 commits into from
Jul 14, 2026
Merged

chore: update aggregated examples for vllm xpu 0.24.0 #11229

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
ecd4191
Bump to vllm xpu 0.24.0
joshuayao Jul 6, 2026
e44e639
rollback ffmpeg installation
joshuayao Jul 6, 2026
28e1655
Rollback vllm xpu upgrade
joshuayao Jul 6, 2026
7e6447c
Merge branch 'main' into vllm_xpu_0_24_0
rmccorm4 Jul 6, 2026
1f0a186
Merge branch 'main' into vllm_xpu_0_24_0
joshuayao Jul 8, 2026
211bce5
Merge branch 'main' into vllm_xpu_0_24_0
joshuayao Jul 13, 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
1 change: 0 additions & 1 deletion examples/backends/vllm/launch/xpu/agg_lmcache_multiproc_xpu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,7 +51,6 @@ DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \
python -m dynamo.vllm --model "$MODEL" --enforce-eager \
--max-model-len "$MAX_MODEL_LEN" \
--max-num-seqs "$MAX_CONCURRENT_SEQS" \
--block-size "${BLOCK_SIZE:-64}" \
${GPU_MEM_ARGS:---gpu-memory-utilization 0.75} \
--kv-transfer-config '{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_both","kv_buffer_device":"xpu"}' &

Expand Down
1 change: 0 additions & 1 deletion examples/backends/vllm/launch/xpu/agg_lmcache_xpu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,6 @@ DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \
python -m dynamo.vllm --model "$MODEL" --enforce-eager \
--max-model-len "$MAX_MODEL_LEN" \
--max-num-seqs "$MAX_CONCURRENT_SEQS" \
--block-size "${BLOCK_SIZE:-64}" \
${GPU_MEM_ARGS:---gpu-memory-utilization 0.75} \
--kv-transfer-config '{"kv_connector":"LMCacheConnectorV1","kv_role":"kv_both","kv_buffer_device":"xpu"}' &

Expand Down
1 change: 0 additions & 1 deletion examples/backends/vllm/launch/xpu/agg_multimodal_xpu.sh
View file
Open in desktop
Comment thread
rmccorm4 marked this conversation as resolved.
Original file line number Diff line number Diff line change
Expand Up @@ -85,7 +85,6 @@ DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \
python -m dynamo.vllm --enable-multimodal --model $MODEL_NAME \
--max-model-len "$MAX_MODEL_LEN" \
--max-num-seqs "$MAX_CONCURRENT_SEQS" \
--block-size "${BLOCK_SIZE:-64}" \
${GPU_MEM_ARGS:---gpu-memory-utilization 0.75} $MODEL_EXTRA_ARGS "${EXTRA_ARGS[@]}" &

# Exit on first worker failure; kill 0 in the EXIT trap tears down the rest
Expand Down
1 change: 0 additions & 1 deletion examples/backends/vllm/launch/xpu/agg_request_planes_xpu.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -66,7 +66,6 @@ DYN_HEALTH_CHECK_ENABLED=true \
python -m dynamo.vllm --model "$MODEL" --enforce-eager \
--max-model-len "$MAX_MODEL_LEN" \
--max-num-seqs "$MAX_CONCURRENT_SEQS" \
--block-size "${BLOCK_SIZE:-64}" \
$GPU_MEM_ARGS &

# Exit on first worker failure; kill 0 in the EXIT trap tears down the rest
Expand Down
1 change: 0 additions & 1 deletion examples/backends/vllm/launch/xpu/agg_xpu.sh
View file
Open in desktop
Comment thread
joshuayao marked this conversation as resolved.
Original file line number Diff line number Diff line change
Expand Up @@ -57,7 +57,6 @@ DYN_SYSTEM_PORT=${DYN_SYSTEM_PORT:-8081} \
python -m dynamo.vllm --model "$MODEL" --enforce-eager \
--max-model-len "$MAX_MODEL_LEN" \
--max-num-seqs "$MAX_CONCURRENT_SEQS" \
--block-size "${BLOCK_SIZE:-64}" \
$GPU_MEM_ARGS "${EXTRA_ARGS[@]}" &

# Exit on first worker failure; kill 0 in the EXIT trap tears down the rest
Expand Down
2 changes: 1 addition & 1 deletion tests/serve/test_vllm_xpu.py
View file
Open in desktop
Comment thread
joshuayao marked this conversation as resolved.
Original file line number Diff line number Diff line change
Expand Up @@ -111,7 +111,7 @@ class VLLMConfig(EngineConfig):
pytest.mark.requested_vllm_kv_cache_bytes(
1_119_388_000
), # KV cache cap (2x safety over min=559_693_824)
pytest.mark.timeout(120), # ~5x observed 24.3s; CI machines are slower
pytest.mark.timeout(420),
Comment thread
joshuayao marked this conversation as resolved.
pytest.mark.post_merge,
],
model="Qwen/Qwen3-0.6B",
Expand Down
Loading