Jeffrey Morgan 68ee42f995 update llama.cpp submodule to `6eeaeba1` (#6039) 9 月之前
..
ext_server 68ee42f995 update llama.cpp submodule to `6eeaeba1` (#6039) 9 月之前
generate 283948c83b Adjust windows ROCm discovery 9 月之前
llama.cpp @ 6eeaeba126 68ee42f995 update llama.cpp submodule to `6eeaeba1` (#6039) 9 月之前
patches 68ee42f995 update llama.cpp submodule to `6eeaeba1` (#6039) 9 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 cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 月之前
ggml.go 5a739ff4cb chatglm graph 9 月之前
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 月之前
gguf.go 4a565cbf94 add chat and generate tests with mock runner 9 月之前
llm.go 10e768826c fix: quant err message (#5616) 9 月之前
llm_darwin_amd64.go e12fff8810 Enable windows error dialog for subprocess startup 9 月之前
llm_darwin_arm64.go e12fff8810 Enable windows error dialog for subprocess startup 9 月之前
llm_linux.go e12fff8810 Enable windows error dialog for subprocess startup 9 月之前
llm_windows.go e12fff8810 Enable windows error dialog for subprocess startup 9 月之前
memory.go 8e0641a9bf handle asymmetric embedding KVs 10 月之前
memory_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) 10 月之前
payload.go 0e982bc1f4 Fix corner cases on tmp cleaner on mac 10 月之前
server.go f3d7a481b7 feat: add support for min_p (resolve #1142) (#1825) 9 月之前
status.go 4d71c559b2 fix error detection by limiting model loading error parsing (#5472) 10 月之前