Jeffrey Morgan de4fc29773 llm: reserve required number of slots for embeddings (#6219) il y a 8 mois
..
ext_server e04c7012c2 update llama.cpp submodule to `1e6f6554` (#6208) il y a 8 mois
generate 283948c83b Adjust windows ROCm discovery il y a 9 mois
llama.cpp @ 1e6f6554aa e04c7012c2 update llama.cpp submodule to `1e6f6554` (#6208) il y a 8 mois
patches e04c7012c2 update llama.cpp submodule to `1e6f6554` (#6208) il y a 8 mois
filetype.go d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) il y a 11 mois
ggla.go 6b252918fb update convert test to check result data il y a 9 mois
ggml.go 6b252918fb update convert test to check result data il y a 9 mois
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) il y a 10 mois
gguf.go df993fa37b comments il y a 9 mois
llm.go b732beba6a lint il y a 9 mois
llm_darwin_amd64.go e12fff8810 Enable windows error dialog for subprocess startup il y a 9 mois
llm_darwin_arm64.go e12fff8810 Enable windows error dialog for subprocess startup il y a 9 mois
llm_linux.go e12fff8810 Enable windows error dialog for subprocess startup il y a 9 mois
llm_windows.go e12fff8810 Enable windows error dialog for subprocess startup il y a 9 mois
memory.go 8e0641a9bf handle asymmetric embedding KVs il y a 10 mois
memory_test.go b732beba6a lint il y a 9 mois
payload.go 0e982bc1f4 Fix corner cases on tmp cleaner on mac il y a 10 mois
server.go de4fc29773 llm: reserve required number of slots for embeddings (#6219) il y a 8 mois
status.go 4d71c559b2 fix error detection by limiting model loading error parsing (#5472) il y a 10 mois