OpenSource/ollama @ upgrade-all

Jeffrey Morgan 3ebd6a83fc update submodule to `cd4fddb29f81d6a1f6d51a0c016bc6b486d68def`		1 年之前
..
ext_server	730dcfcc7a Refine debug logging for llm	1 年之前
generate	a64570dcae Fix clearing kv cache between requests with the same prompt (#2186)	1 年之前
llama.cpp @ cd4fddb29f	3ebd6a83fc update submodule to `cd4fddb29f81d6a1f6d51a0c016bc6b486d68def`	1 年之前
patches	a64570dcae Fix clearing kv cache between requests with the same prompt (#2186)	1 年之前
dyn_ext_server.c	6a042438af Switch to local dlopen symbols	1 年之前
dyn_ext_server.go	a64570dcae Fix clearing kv cache between requests with the same prompt (#2186)	1 年之前
dyn_ext_server.h	39928a42e8 Always dynamically load the llm server library	1 年之前
ggml.go	eaed6f8c45 add max context length check	1 年之前
gguf.go	cd22855ef8 refactor tensor read	1 年之前
llama.go	4a33cede20 remove unused fields and functions	1 年之前
llm.go	4458efb73a Load all layers on `arm64` macOS if model is small enough (#2149)	1 年之前
payload_common.go	dc88cc3981 use `gzip` for runner embedding (#2067)	1 年之前
payload_darwin_amd64.go	1b249748ab Add multiple CPU variants for Intel Mac	1 年之前
payload_darwin_arm64.go	1b249748ab Add multiple CPU variants for Intel Mac	1 年之前
payload_linux.go	1b249748ab Add multiple CPU variants for Intel Mac	1 年之前
payload_test.go	7427fa1387 Fix up the CPU fallback selection	1 年之前
payload_windows.go	1b249748ab Add multiple CPU variants for Intel Mac	1 年之前
utils.go	fccf8d179f partial decode ggml bin for more info	1 年之前