OpenSource/ollama

作者	SHA1 備註	提交日期
Daniel Hiltgen	34b9db5afc Request and model concurrency	1 年之前
Michael Yang	26df674785 scale graph based on gpu count	1 年之前
Michael Yang	41a272de9f darwin: no partial offloading if required memory greater than system	1 年之前
Michael Yang	7e33a017c0 partial offloading	1 年之前
Daniel Hiltgen	be330174dd Allow setting max vram for workarounds	1 年之前
peanut256	a189810df6 Determine max VRAM on macOS using `recommendedMaxWorkingSetSize` (#2354)	1 年之前
Daniel Hiltgen	7427fa1387 Fix up the CPU fallback selection	1 年之前
Daniel Hiltgen	39928a42e8 Always dynamically load the llm server library	1 年之前
Daniel Hiltgen	d88c527be3 Build multiple CPU variants and pick the best	1 年之前
Jeffrey Morgan	c336693f07 calculate overhead based number of gpu devices (#1875)	1 年之前
Jeffrey Morgan	08f1e18965 Offload layers to GPU based on new model size estimates (#1850)	1 年之前
Jeffrey Morgan	c7ea8f237e set `num_gpu` to 1 only by default on darwin arm64 (#1771)	1 年之前
Daniel Hiltgen	a2ad952440 Fix windows system memory lookup	1 年之前
Daniel Hiltgen	d966b730ac Switch windows build to fully dynamic	1 年之前
Daniel Hiltgen	7555ea44f8 Revamp the dynamic library shim	1 年之前
Daniel Hiltgen	6558f94ed0 Fix darwin intel build	1 年之前
Daniel Hiltgen	35934b2e05 Adapted rocm support to cgo based llama.cpp	1 年之前