OpenSource/ollama

作者	SHA1 备注	提交日期
Daniel Hiltgen	17ce203a26 Merge pull request #4875 from dhiltgen/rocm_gfx900_workaround	10 月之前
Daniel Hiltgen	6be309e1bd Centralize GPU configuration vars	1 年之前
Daniel Hiltgen	da3bf23354 Workaround gfx900 SDMA bugs	11 月之前
Daniel Hiltgen	6f351bf586 review comments and coverage	11 月之前
Daniel Hiltgen	6fd04ca922 Improve multi-gpu handling at the limit	11 月之前
Daniel Hiltgen	43ed358f9a Refine GPU discovery to bootstrap once	11 月之前
Daniel Hiltgen	b32ebb4f29 Use DRM driver for VRAM info for amd	11 月之前
Daniel Hiltgen	8727a9c140 Record more GPU information	1 年之前
Daniel Hiltgen	e592e8fccb Support Fedoras standard ROCm location	1 年之前
Daniel Hiltgen	0d6687f84c AMD gfx patch rev is hex	1 年之前
Daniel Hiltgen	34b9db5afc Request and model concurrency	1 年之前
Daniel Hiltgen	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前
Michael Yang	f31f2bedf4 Update troubleshooting link	1 年之前
Daniel Hiltgen	82b0c7c27e Fix iGPU detection for linux	1 年之前
Daniel Hiltgen	bc13da2bfe Avoid rocm runner and dependency clash	1 年之前
Daniel Hiltgen	00ec269321 Add ollama executable peer dir for rocm	1 年之前
Daniel Hiltgen	4a5c9b8035 Finish unwinding idempotent payload logic	1 年之前
Daniel Hiltgen	6c5ccb11f9 Revamp ROCm support	1 年之前