vllm/csrc/quantization at 3eeb148f467e3619e8890b1a5ebe86a173f91bc9 - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-07-22 13:00:10 +08:00

Files

T

History

Alexander MatveevandGitHub 75acdaa4b6 [Kernel] Increase precision of GPTQ/AWQ Marlin kernel (#6795 )

2024-07-27 17:52:33 -04:00

..

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

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

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

2024-06-09 16:23:30 -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

[Bug Fix] Illegal memory access, FP8 Llama 3.1 405b (#6852 )

2024-07-27 02:27:44 +00:00

[Bugfix][Kernel] Promote another index to int64_t (#6838 )

2024-07-26 18:41:04 +00:00

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

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

[Kernel] Increase precision of GPTQ/AWQ Marlin kernel (#6795 )

2024-07-27 17:52:33 -04:00

[Kernel][Core] Add AWQ support to the Marlin kernel (#6612 )

2024-07-21 19:41:42 -04:00

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

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