Josh Yan 0e1ec461f9 import há 8 meses atrás
..
ext_server 90ca84172c Fix embeddings memory corruption (#6467) há 8 meses atrás
generate 0b03b9c32f llm: Align cmake define for cuda no peer copy (#6455) há 8 meses atrás
llama.cpp @ 1e6f6554aa e04c7012c2 update llama.cpp submodule to `1e6f6554` (#6208) há 8 meses atrás
patches 90ca84172c Fix embeddings memory corruption (#6467) há 8 meses atrás
filetype.go d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) há 11 meses atrás
ggla.go 6b252918fb update convert test to check result data há 9 meses atrás
ggml.go 0c819e167b convert safetensor adapters into GGUF (#6327) há 8 meses atrás
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) há 10 meses atrás
gguf.go 0e1ec461f9 import há 8 meses atrás
llm.go b732beba6a lint há 9 meses atrás
llm_darwin_amd64.go e12fff8810 Enable windows error dialog for subprocess startup há 9 meses atrás
llm_darwin_arm64.go e12fff8810 Enable windows error dialog for subprocess startup há 9 meses atrás
llm_linux.go e12fff8810 Enable windows error dialog for subprocess startup há 9 meses atrás
llm_windows.go e12fff8810 Enable windows error dialog for subprocess startup há 9 meses atrás
memory.go 8e0641a9bf handle asymmetric embedding KVs há 10 meses atrás
memory_test.go 01b20fe6f1 lint há 8 meses atrás
payload.go d470ebe78b Add Jetson cuda variants for arm há 8 meses atrás
server.go 397cae7962 llm: fix typo in comment (#6530) há 8 meses atrás
status.go 04210aa6dd Catch one more error log há 9 meses atrás