OpenSource/ollama @ jmorganca/llama-cpp-7c26775

jmorganca 9b5b69c00f llm: update llama.cpp submodule to `7c26775`		10 月之前
..
ext_server	fb9cdfa723 Fix server.cpp for the new cuda build macros	10 月之前
generate	0577af98f4 More parallelism on windows generate	10 月之前
llama.cpp @ 7c26775adb	9b5b69c00f llm: update llama.cpp submodule to `7c26775`	10 月之前
patches	ce0dc33cb8 llm: patch to fix qwen 2 temporarily on nvidia (#4897)	11 月之前
filetype.go	d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322)	11 月之前
ggla.go	171eb040fc simplify safetensors reading	11 月之前
ggml.go	6fd04ca922 Improve multi-gpu handling at the limit	10 月之前
gguf.go	7bdcd1da94 Revert "Merge pull request #4938 from ollama/mxyng/fix-byte-order"	10 月之前
llm.go	829ff87bd1 revert tokenize ffi (#4761)	11 月之前
llm_darwin_amd64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前
llm_darwin_arm64.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前
llm_linux.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前
llm_windows.go	058f6cd2cc Move nested payloads to installer and zip file on windows	1 年之前
memory.go	17df6520c8 Remove mmap related output calc logic	10 月之前
memory_test.go	6f351bf586 review comments and coverage	10 月之前
payload.go	6f351bf586 review comments and coverage	10 月之前
server.go	da3bf23354 Workaround gfx900 SDMA bugs	10 月之前
status.go	58d95cc9bd Switch back to subprocessing for llama.cpp	1 年之前