OpenSource/ollama @ jmorganca/done-reason

Michael Yang 26df674785 scale graph based on gpu count		1 年之前
..
amd_common.go	82b0c7c27e Fix iGPU detection for linux	1 年之前
amd_hip_windows.go	6c5ccb11f9 Revamp ROCm support	1 年之前
amd_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前
amd_windows.go	4a5c9b8035 Finish unwinding idempotent payload logic	1 年之前
assets.go	0a74cb31d5 Safeguard for noexec	1 年之前
cpu_common.go	fedd705aea Mechanical switch from log to slog	1 年之前
gpu.go	7e33a017c0 partial offloading	1 年之前
gpu_darwin.go	26df674785 scale graph based on gpu count	1 年之前
gpu_info.h	dfc6721b20 add support for libcudart.so for CUDA devices (adds Jetson support)	1 年之前
gpu_info_cpu.c	c336693f07 calculate overhead based number of gpu devices (#1875)	1 年之前
gpu_info_cudart.c	526d4eb204 Release gpu discovery library after use	1 年之前
gpu_info_cudart.h	526d4eb204 Release gpu discovery library after use	1 年之前
gpu_info_darwin.h	41a272de9f darwin: no partial offloading if required memory greater than system	1 年之前
gpu_info_darwin.m	41a272de9f darwin: no partial offloading if required memory greater than system	1 年之前
gpu_info_nvml.c	526d4eb204 Release gpu discovery library after use	1 年之前
gpu_info_nvml.h	526d4eb204 Release gpu discovery library after use	1 年之前
gpu_test.go	de2fbdec99 Merge pull request #1819 from dhiltgen/multi_variant	1 年之前
types.go	7e33a017c0 partial offloading	1 年之前