Mirrors
/
hf_text-generation-inference
mirror of https://github.com/huggingface/text-generation-inference.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity
hf_text-generation-inference/server/exllama_kernels/exllama_kernels
History
OlivierDehaene 0d794af6a5
feat: experimental support for cuda graphs (#1428) 
Co-authored-by: Nicolas Patry <patry.nicolas@protonmail.com>
 		2024-02-12 10:09:29 +01:00
..
cuda_func feat: experimental support for cuda graphs (#1428) 2024-02-12 10:09:29 +01:00
cu_compat.cuh GPTQ support on ROCm (#1489) 2024-01-26 16:27:44 +01:00
cuda_buffers.cu feat(server): Add exllama GPTQ CUDA kernel support #553 (#666) 2023-07-21 10:59:00 +02:00
cuda_buffers.cuh feat(server): Add exllama GPTQ CUDA kernel support #553 (#666) 2023-07-21 10:59:00 +02:00
exllama_ext.cpp feat: experimental support for cuda graphs (#1428) 2024-02-12 10:09:29 +01:00
hip_compat.cuh GPTQ support on ROCm (#1489) 2024-01-26 16:27:44 +01:00
matrix.cuh feat(server): Add exllama GPTQ CUDA kernel support #553 (#666) 2023-07-21 10:59:00 +02:00
tuning.h feat(server): Add exllama GPTQ CUDA kernel support #553 (#666) 2023-07-21 10:59:00 +02:00
util.cuh GPTQ support on ROCm (#1489) 2024-01-26 16:27:44 +01:00