Daniel Hiltgen 30a7d7096c Bump VRAM buffer back up ...

Under stress scenarios we're seeing OOMs so this should help stabilize
the allocations under heavy concurrency stress.

2024-05-10 09:15:28 -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

Record more GPU information

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

amd_windows.go

Record more GPU information

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

assets.go

Centralize server config handling

2024-05-05 16:49:50 -07:00

cpu_common.go

Wait for GPU free memory reporting to converge

2024-05-09 14:56:01 -07:00

cuda_common.go

Request and model concurrency

2024-04-22 19:29:12 -07:00

gpu_darwin.go

Bump VRAM buffer back up

2024-05-10 09:15:28 -07:00

gpu_info_cpu.c

Record more GPU information

2024-05-09 14:18:14 -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

Record more GPU information

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

gpu_info_nvcuda.h

Record more GPU information

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

gpu_info.h

Record more GPU information

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

gpu_test.go

Request and model concurrency

2024-04-22 19:29:12 -07:00

gpu.go

Bump VRAM buffer back up

2024-05-10 09:15:28 -07:00

types.go

Record more GPU information

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