Gahow Wang
445e491123
third_party/vllm/ now tracked in git for direct patch management.
Based on vLLM v0.18.1 release with one patch applied:
vllm/v1/core/sched/scheduler.py:
Replace fatal assert with graceful skip when KV transfer callback
arrives for an already-aborted request during PD disaggregated serving.
Future vLLM modifications should be made directly in third_party/vllm/
and committed normally. The patches/ directory is kept as documentation
of what changed from upstream.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
47 lines
1.7 KiB
YAML
47 lines
1.7 KiB
YAML
group: Quantization
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: Quantization
|
|
timeout_in_minutes: 90
|
|
source_file_dependencies:
|
|
- csrc/
|
|
- vllm/model_executor/layers/quantization
|
|
- tests/quantization
|
|
commands:
|
|
# temporary install here since we need nightly, will move to requirements/test.in
|
|
# after torchao 0.12 release, and pin a working version of torchao nightly here
|
|
|
|
# since torchao nightly is only compatible with torch nightly currently
|
|
# https://github.com/pytorch/ao/issues/2919, we'll have to skip new torchao tests for now
|
|
# we can only upgrade after this is resolved
|
|
# TODO(jerryzh168): resolve the above comment
|
|
- uv pip install --system torchao==0.14.1 --index-url https://download.pytorch.org/whl/cu129
|
|
- uv pip install --system conch-triton-kernels
|
|
- VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
|
|
|
|
- label: Quantized MoE Test (B200)
|
|
timeout_in_minutes: 60
|
|
working_dir: "/vllm-workspace/"
|
|
device: b200
|
|
source_file_dependencies:
|
|
- tests/quantization/test_blackwell_moe.py
|
|
- vllm/model_executor/models/deepseek_v2.py
|
|
- vllm/model_executor/models/gpt_oss.py
|
|
- vllm/model_executor/models/llama4.py
|
|
- vllm/model_executor/layers/fused_moe
|
|
- vllm/model_executor/layers/quantization/compressed_tensors
|
|
- vllm/model_executor/layers/quantization/modelopt.py
|
|
- vllm/model_executor/layers/quantization/mxfp4.py
|
|
- vllm/v1/attention/backends/flashinfer.py
|
|
commands:
|
|
- pytest -s -v tests/quantization/test_blackwell_moe.py
|
|
|
|
- label: Quantized Models Test
|
|
timeout_in_minutes: 60
|
|
source_file_dependencies:
|
|
- vllm/model_executor/layers/quantization
|
|
- tests/models/quantization
|
|
commands:
|
|
- pytest -v -s models/quantization
|