vllm/csrc/quantization at d3d9cb6e4b8185b4e56e1dda92c6fc31cdc05de1 - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-07-08 15:29:28 +08:00

Files

T

History

Lucas Wilkinson 6aa33cb2dd [Misc] Use scalar type to dispatch to different gptq_marlin kernels (#7323 )

2024-08-12 14:40:13 -04:00

..

[Kernel] Squash a few more warnings (#6914 )

2024-07-30 13:50:42 -04:00

[CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001 )

2024-08-05 16:00:01 -04:00

compressed_tensors

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047 )

2024-06-09 16:23:30 -04:00

[Kernel] Add per-tensor and per-token AZP epilogues (#5941 )

2024-08-06 18:17:08 +00:00

[CI/Build] Suppress divide-by-zero and missing return statement warnings (#7001 )

2024-08-05 16:00:01 -04:00

[Core] Support loading GGUF model (#5191 )

2024-08-05 17:54:23 -06:00

[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047 )

2024-06-09 16:23:30 -04:00

[Misc] Use scalar type to dispatch to different gptq_marlin kernels (#7323 )

2024-08-12 14:40:13 -04:00

[Misc] Disambiguate quantized types via a new ScalarType (#6396 )

2024-08-02 13:51:58 -07:00

[Kernel] Squash a few more warnings (#6914 )

2024-07-30 13:50:42 -04:00