Roy Han 80cba42ab2 Update docs преди 10 месеца
..
ext_server b9f5e16c80 Introduce `/api/embed` endpoint supporting batch embedding (#5127) преди 9 месеца
generate efbf41ed81 llm: dont link cuda with compat libs (#5621) преди 9 месеца
llama.cpp @ a8db2a9ce6 80cba42ab2 Update docs преди 9 месеца
patches 571dc61955 Update llama.cpp submodule to `a8db2a9c` (#5530) преди 9 месеца
filetype.go d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) преди 11 месеца
ggla.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) преди 10 месеца
ggml.go 5a739ff4cb chatglm graph преди 9 месеца
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) преди 10 месеца
gguf.go 4a565cbf94 add chat and generate tests with mock runner преди 9 месеца
llm.go 10e768826c fix: quant err message (#5616) преди 9 месеца
llm_darwin_amd64.go 58d95cc9bd Switch back to subprocessing for llama.cpp преди 1 година
llm_darwin_arm64.go 58d95cc9bd Switch back to subprocessing for llama.cpp преди 1 година
llm_linux.go 58d95cc9bd Switch back to subprocessing for llama.cpp преди 1 година
llm_windows.go 058f6cd2cc Move nested payloads to installer and zip file on windows преди 1 година
memory.go 8e0641a9bf handle asymmetric embedding KVs преди 10 месеца
memory_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) преди 10 месеца
payload.go 0e982bc1f4 Fix corner cases on tmp cleaner on mac преди 10 месеца
server.go b9f5e16c80 Introduce `/api/embed` endpoint supporting batch embedding (#5127) преди 9 месеца
status.go 4d71c559b2 fix error detection by limiting model loading error parsing (#5472) преди 10 месеца