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>
33 lines
1.3 KiB
YAML
33 lines
1.3 KiB
YAML
group: LoRA
|
|
depends_on:
|
|
- image-build
|
|
steps:
|
|
- label: LoRA %N
|
|
timeout_in_minutes: 30
|
|
source_file_dependencies:
|
|
- vllm/lora
|
|
- tests/lora
|
|
commands:
|
|
- pytest -v -s lora --shard-id=$$BUILDKITE_PARALLEL_JOB --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --ignore=lora/test_chatglm3_tp.py --ignore=lora/test_llama_tp.py --ignore=lora/test_llm_with_multi_loras.py --ignore=lora/test_olmoe_tp.py --ignore=lora/test_deepseekv2_tp.py --ignore=lora/test_gptoss_tp.py --ignore=lora/test_qwen3moe_tp.py
|
|
parallelism: 4
|
|
|
|
|
|
- label: LoRA TP (Distributed)
|
|
timeout_in_minutes: 30
|
|
num_devices: 4
|
|
source_file_dependencies:
|
|
- vllm/lora
|
|
- tests/lora
|
|
commands:
|
|
# FIXIT: find out which code initialize cuda before running the test
|
|
# before the fix, we need to use spawn to test it
|
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
|
# Alot of these tests are on the edge of OOMing
|
|
- export PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True
|
|
# There is some Tensor Parallelism related processing logic in LoRA that
|
|
# requires multi-GPU testing for validation.
|
|
- pytest -v -s -x lora/test_chatglm3_tp.py
|
|
- pytest -v -s -x lora/test_llama_tp.py
|
|
- pytest -v -s -x lora/test_llm_with_multi_loras.py
|
|
- pytest -v -s -x lora/test_olmoe_tp.py
|
|
- pytest -v -s -x lora/test_gptoss_tp.py |