ollama/gpu
Daniel Hiltgen 089daaeabc Add CUDA Driver API for GPU discovery
We're seeing some corner cases with cudart which might be resolved by
switching to the driver API which comes bundled with the driver package
2024-04-30 18:00:45 -07:00
..
amd_common.go Request and model concurrency 2024-04-22 19:29:12 -07:00
amd_hip_windows.go Request and model concurrency 2024-04-22 19:29:12 -07:00
amd_linux.go AMD gfx patch rev is hex 2024-04-24 09:43:52 -07:00
amd_windows.go AMD gfx patch rev is hex 2024-04-24 09:43:52 -07:00
assets.go Fix relative path lookup 2024-04-29 16:00:08 -07:00
cpu_common.go Mechanical switch from log to slog 2024-01-18 14:12:57 -08:00
cuda_common.go Request and model concurrency 2024-04-22 19:29:12 -07:00
gpu.go Add CUDA Driver API for GPU discovery 2024-04-30 18:00:45 -07:00
gpu_darwin.go Request and model concurrency 2024-04-22 19:29:12 -07:00
gpu_info.h Add CUDA Driver API for GPU discovery 2024-04-30 18:00:45 -07:00
gpu_info_cpu.c Request and model concurrency 2024-04-22 19:29:12 -07:00
gpu_info_cudart.c Request and model concurrency 2024-04-22 19:29:12 -07:00
gpu_info_cudart.h Add CUDA Driver API for GPU discovery 2024-04-30 18:00:45 -07:00
gpu_info_darwin.h darwin: no partial offloading if required memory greater than system 2024-04-16 11:22:38 -07:00
gpu_info_darwin.m darwin: no partial offloading if required memory greater than system 2024-04-16 11:22:38 -07:00
gpu_info_nvcuda.c Add CUDA Driver API for GPU discovery 2024-04-30 18:00:45 -07:00
gpu_info_nvcuda.h Add CUDA Driver API for GPU discovery 2024-04-30 18:00:45 -07:00
gpu_test.go Request and model concurrency 2024-04-22 19:29:12 -07:00
types.go Request and model concurrency 2024-04-22 19:29:12 -07:00