anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[Bugfix][XPU] Fix free-memory abort and num_speculative_steps crash on XPU (#5330)

Browse Source 
Signed-off-by: Joshna Medisetty <joshna.medisetty@intel.com>
Co-authored-by: Chendi.Xue <chendi.xue@intel.com>
This commit is contained in:
Joshna-MedisettyandChendi.Xue authored and GitHub committed 2026-07-23 17:17:00 +00:00
1 parent 4c23a3164b
commit 0fe5d73a63
5 files changed
+25 -2
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/intel/scripts/run-xpu-test.sh
+1 -1
View File
@@ -74,6 +74,6 @@ time timeout -k 30 30m docker run \
cd /workspace/vllm-omni
pytest -v -s -m "core_model and xpu and B60"
pytest -v -s tests/diffusion/quantization/test_mxfp8_config.py
export VLLM_XPU_USE_SAMPLER_KERNEL=0 # NOTE: Remove this after vLLM v0.21.1 is merged. Fixes Qwen2-5 omni-expansion tests.
pytest -v -s -m "advanced_model and xpu and B60"
pytest -v -s -m "omni and xpu and B60"
'