Sam 1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279) 4 months ago
..
amd_common.go d7c94e0ca6 Better support for AMD multi-GPU on linux (#7212) 6 months ago
amd_hip_windows.go d7c94e0ca6 Better support for AMD multi-GPU on linux (#7212) 6 months ago
amd_linux.go df011054fa Jetpack support for Go server (#7217) 5 months ago
amd_windows.go df011054fa Jetpack support for Go server (#7217) 5 months ago
cpu_common.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
cuda_common.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu.go df011054fa Jetpack support for Go server (#7217) 5 months ago
gpu_darwin.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info.h 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_cudart.c 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_cudart.h 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_darwin.h 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_darwin.m 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_nvcuda.c b111aa5a91 Debug logging for nvcuda init (#7532) 5 months ago
gpu_info_nvcuda.h 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_nvml.c 29ab9fa7d7 nvidia libs have inconsistent ordering (#7473) 6 months ago
gpu_info_nvml.h 29ab9fa7d7 nvidia libs have inconsistent ordering (#7473) 6 months ago
gpu_info_oneapi.c 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_info_oneapi.h 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_linux.go 16f4eabe2d Refine default thread selection for NUMA systems (#7322) 6 months ago
gpu_linux_test.go 16f4eabe2d Refine default thread selection for NUMA systems (#7322) 6 months ago
gpu_oneapi.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_test.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_windows.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
gpu_windows_test.go 05cd82ef94 Rename gpu package discover (#7143) 6 months ago
types.go 1bdab9fdb1 llm: introduce k/v context quantization (vRAM improvements) (#6279) 4 months ago