vLLM/tests/models at 83bdcb6ac32f22f20fd3a60ba67064a0b462801d - vLLM

Files

T

[ci][distributed] fix some cuda init that makes it necessary to use spawn (#5991)

2024-06-30 08:06:13 +00:00

__init__.py

…

test_aqlm.py

…

test_big_models.py

2024-06-30 11:44:25 +08:00

test_compressed_tensors.py

2024-06-29 21:12:58 +08:00

test_embedding.py

…

test_fp8.py

…

test_gptq_marlin_24.py

…

test_gptq_marlin.py

…

test_llava_next.py

2024-06-30 11:44:25 +08:00

test_llava.py

2024-06-30 08:06:13 +00:00

test_marlin.py

…

test_mistral.py

…

test_models.py

2024-06-30 11:44:25 +08:00

test_oot_registration.py

…

test_phi3v.py

2024-06-30 08:06:13 +00:00

test_registry.py

…

utils.py

2024-06-30 11:44:25 +08:00