Kevin H. Luu 600a039f57 [CI] Shard Multi-Modal Models (Standard) into 4 parallel jobs (#37014) ...

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>

2026-03-14 08:26:54 +00:00

..

hardware_tests

[UX] Improve UX of CPU backend (#36968)

2026-03-14 09:27:29 +08:00

image_build

[UX] Improve UX of CPU backend (#36968)

2026-03-14 09:27:29 +08:00

lm-eval-harness

[ROCm][CI] Prep Tests For Change To ROCM_ATTN As New Default Backend On ROCm (#36025)

2026-03-09 13:27:55 -05:00

performance-benchmarks

more models for vLLM Benchmark Suite (#35086)

2026-03-12 11:36:51 +08:00

scripts

[UX] Improve UX of CPU backend (#36968)

2026-03-14 09:27:29 +08:00

test_areas

[CI] Shard Multi-Modal Models (Standard) into 4 parallel jobs (#37014)

2026-03-14 08:26:54 +00:00

.pipeline_gen_v2

[CI] minor fixes to pipeline generator and tests (#33151)

2026-01-27 17:04:02 -08:00

check-wheel-size.py

[CI] Raise VLLM_MAX_SIZE_MB to 500 due to failing Build wheel - CUDA 12.9 (#26722)

2025-10-14 10:52:05 -07:00

ci_config.yaml

[ci] Sync test areas with test-pipeline.yaml and enable new pipeline generator (#33080)

2026-01-26 12:28:20 -08:00

release-pipeline.yaml

[UX] Improve UX of CPU backend (#36968)

2026-03-14 09:27:29 +08:00

test-amd.yaml

[CI] Split V1 e2e + engine (1 GPU) into separate jobs (#36945)

2026-03-13 14:16:02 -07:00

test-pipeline.yaml

Deprecate test-pipeline.yaml (#34864)

2026-02-19 02:15:27 +00:00