Daniel Hiltgen f6f759fc5f Detect CUDA OS Overhead ...

This adds logic to detect skew between the driver and
management library which can be attributed to OS overhead
and records that so we can adjust subsequent management
library free VRAM updates and avoid OOM scenarios.

2024-07-09 12:21:50 -07:00

..

amd_common.go

Support Fedoras standard ROCm location

2024-05-01 15:47:12 -07:00

amd_hip_windows.go

Record more GPU information

2024-05-09 14:18:14 -07:00

amd_linux.go

Merge pull request #4875 from dhiltgen/rocm_gfx900_workaround

2024-06-15 07:38:58 -07:00

amd_windows.go

Disable concurrency for AMD + Windows

2024-06-21 15:45:05 -07:00

assets.go

err!=nil check

2024-06-20 09:30:59 -07:00

cpu_common.go

review comments and coverage

2024-06-14 14:55:50 -07:00

cuda_common.go

lint linux

2024-06-04 11:13:30 -07:00

gpu_darwin.go

gpu: report system free memory instead of 0 (#5521)

2024-07-06 19:35:04 -04:00

gpu_info_cudart.c

Fix bad symbol load detection

2024-06-19 08:39:07 -07:00

gpu_info_cudart.h

Refine GPU discovery to bootstrap once

2024-06-14 14:51:40 -07:00

gpu_info_darwin.h

gpu: report system free memory instead of 0 (#5521)

2024-07-06 19:35:04 -04:00

gpu_info_darwin.m

gpu: report system free memory instead of 0 (#5521)

2024-07-06 19:35:04 -04:00

gpu_info_nvcuda.c

Better nvidia GPU discovery logging

2024-07-03 10:50:40 -07:00

gpu_info_nvcuda.h

Better nvidia GPU discovery logging

2024-07-03 10:50:40 -07:00

gpu_info_nvml.c

Fix bad symbol load detection

2024-06-19 08:39:07 -07:00

gpu_info_nvml.h

Reintroduce nvidia nvml library for windows

2024-06-14 14:51:40 -07:00

gpu_info_oneapi.c

get real func ptr.

2024-06-19 09:00:51 +08:00

gpu_info_oneapi.h

review comments and coverage

2024-06-14 14:55:50 -07:00

gpu_info.h

Reintroduce nvidia nvml library for windows

2024-06-14 14:51:40 -07:00

gpu_linux.go

review comments and coverage

2024-06-14 14:55:50 -07:00

gpu_oneapi.go

support ollama run on Intel GPUs

2024-05-24 11:18:27 +08:00

gpu_test.go

lint

2024-06-04 11:13:30 -07:00

gpu_windows.go

review comments and coverage

2024-06-14 14:55:50 -07:00

gpu.go

Detect CUDA OS Overhead

2024-07-09 12:21:50 -07:00

types.go

Detect CUDA OS Overhead

2024-07-09 12:21:50 -07:00