Josh Yan cc17b02b23 update 8 달 전
..
ext_server 90ca84172c Fix embeddings memory corruption (#6467) 8 달 전
generate 0b03b9c32f llm: Align cmake define for cuda no peer copy (#6455) 8 달 전
llama.cpp @ 1e6f6554aa e04c7012c2 update llama.cpp submodule to `1e6f6554` (#6208) 8 달 전
patches de9b21b472 quantize progress 8 달 전
filetype.go d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) 11 달 전
ggla.go 6b252918fb update convert test to check result data 9 달 전
ggml.go 0c819e167b convert safetensor adapters into GGUF (#6327) 8 달 전
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 달 전
gguf.go 6ffb5cb017 add conversion for microsoft phi 3 mini/medium 4k, 128 8 달 전
llama.h de9b21b472 quantize progress 8 달 전
llm.go cc17b02b23 update 8 달 전
llm_darwin_amd64.go e12fff8810 Enable windows error dialog for subprocess startup 9 달 전
llm_darwin_arm64.go e12fff8810 Enable windows error dialog for subprocess startup 9 달 전
llm_linux.go e12fff8810 Enable windows error dialog for subprocess startup 9 달 전
llm_windows.go e12fff8810 Enable windows error dialog for subprocess startup 9 달 전
memory.go 8e0641a9bf handle asymmetric embedding KVs 10 달 전
memory_test.go 77903ab8b4 llama3.1 8 달 전
payload.go d470ebe78b Add Jetson cuda variants for arm 8 달 전
server.go 397cae7962 llm: fix typo in comment (#6530) 8 달 전
status.go 04210aa6dd Catch one more error log 8 달 전