CI: add vllm-test-init and vllm-test-transformers jobs on dedicated runners #47934
Test vLLM CI on larger runner with test_init and test_transformers en…
106704ce
Trigger tests_processors CI run
83796164
Split test_initialization into 8-shard matrix job; add HF_HOME env
39150c02
Trigger vLLM CI run
3016956d
CI: isolate JambaForCausalLM test (1 shard) to debug mamba_mixer Inde…
d1b42c76
CI: switch isolated test to FalconMambaForCausalLM (same mamba_mixer …
28c8c8f0
CI: patch mamba_mixer conv1d weight.view to handle 2D dummy-loaded we…
bb11cc6f
CI: patch mamba_mixer out_proj transpose contiguous for CPU onednn_mm
86876043
CI: fix mamba_mixer sed patch (preserve closing paren of out_proj call)
3b93f3fc
CI: add detailed vLLM upstream bug comments for mamba_mixer CPU patches
50c0aff6
CI: add GPU job to verify mamba_mixer bugs are CPU-specific
7ea71ffc
CI: fix GPU test-init job (no curl, shell bash, ipc host, pip not uv)
9ec6ff7e
CI: install vLLM from CUDA 13.0 nightly wheel for GPU test job
956afd7c
CI: unset VLLM_TARGET_DEVICE for GPU job, add shell bash to pytest step
25b7820f
CI: use PyPI vllm for GPU job (nightly wheel has broken _C_stable_lib…
cf80878a
CI: disable GPU test-init job (vllm._C_stable_libtorch ABI mismatch)
c1afe040
CI: run test_can_initialize_small_subset (8 shards), comment out mamb…
3e79942f
CI: reduce vllm-test-init to 4 shards (small subset has only 12 tests)
020c544c
CI: skip Gemma3nForCausalLM in vllm-test-init (hangs on shm_broadcast)
3e4f31d7
CI: disable vllm-test-init job (Gemma3nForCausalLM hangs on shm_broad…
f268064f
CI: add vllm-test-transformers job on dedicated aws-m8i-8xl-cache runner
67aadbde
CI: add sharding (4 shards) to vllm-test-transformers job
0f68b8c0
CI: add sentence-transformers to vllm-test-transformers install
ea17f630
CI: add comment to vllm-test-transformers gpu_memory patch step
e8f5c364
CI: re-enable vllm-test-init, vllm-multimodal-processing, and inline …
8f029e5e
CI: revert vllm job to 2xl runner, drop gpu_memory patches, restore i…
9f1f8f55
CI: move vllm and multimodal jobs to 8xl runner, restore gpu_memory p…
27cae247
CI: document why all vllm jobs use aws-m8i-8xl-cache runner
88511116
CI: revert qwen3_asr test change, clean up comments
5f0b7ad9
CI: clarify why vllm-test-init uses 8xl runner
242949d1
ydshieh
force pushed
from
34f200c7
to
242949d1
98 days ago
CI: remove stale comments from gpu_memory patch steps
6e2a05bc
ydshieh
merged
85577dbb
into main 98 days ago
ydshieh
deleted the vllm_ci_test branch 98 days ago
Assignees
No one assigned
Login to write a write a comment.
Login via GitHub