Update vLLM wheel version and adjust GPU memory utilization in CI configuration

- Updated the vLLM wheel commit hash in Dockerfile.ci to a60985b07eaf0fefa4c353ad2309b745707591ed.
- Modified the mock shared memory handle name in test_basic_connectors.py for clarity.
- Increased GPU memory utilization to 0.9 and adjusted max_num_batched_tokens to 4096 in qwen2_5_omni_ci.yaml to enable testing on H800.
- Refactored GPU model runner classes to remove deprecated activate_lora parameter and ensure compatibility with num_active_loras.
- Enhanced request handling in the OmniGPUModelRunner class to improve streaming request updates.

Signed-off-by: tzhouam <tzhouam@connect.ust.hk>
This commit is contained in:
tzhouam committed 2026-03-02 03:08:45 +00:00
1 parent 26744bcb35
commit 473d3ecd29
5 files changed
+44 -41

No files matched your search

+2 -2
View File
@@ -14,11 +14,11 @@ RUN apt-get update && \
# Install vLLM wheel for the specific commit
# URL format: https://wheels.vllm.ai/<commit_hash>/
# Current vLLM wheel commit: 6042e66cd5304fc043d96aaa0c22d56f939af320
# Current vLLM wheel commit: a60985b07eaf0fefa4c353ad2309b745707591ed
# Note: --prerelease=allow is required because nightly/commit wheels use
# pre-release version numbers (e.g. 2.10.0.dev...) which uv ignores by default,
# causing it to fall back to the older stable release from PyPI.
RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/6042e66cd5304fc043d96aaa0c22d56f939af320
RUN uv pip install --system --upgrade --force-reinstall --prerelease=allow vllm --extra-index-url https://wheels.vllm.ai/a60985b07eaf0fefa4c353ad2309b745707591ed
RUN uv pip uninstall --system nvidia-cublas-cu12
# Install vllm-omni into the same uv-managed Python environment used by the base image.