Jeffrey Morgan bbf8f102ee Revert "llm(llama): pass rope factors (#5924)" (#5963) пре 9 месеци
..
ext_server b9f5e16c80 Introduce `/api/embed` endpoint supporting batch embedding (#5127) пре 9 месеци
generate 283948c83b Adjust windows ROCm discovery пре 9 месеци
llama.cpp @ d94c6e0ccb f8fedbda20 Update llama.cpp submodule commit to `d94c6e0c` (#5805) пре 9 месеци
patches bbf8f102ee Revert "llm(llama): pass rope factors (#5924)" (#5963) пре 9 месеци
filetype.go d6f692ad1a Add support for IQ1_S, IQ3_S, IQ2_S, IQ4_XS. IQ4_NL (#4322) пре 11 месеци
ggla.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) пре 10 месеци
ggml.go 5a739ff4cb chatglm graph пре 9 месеци
ggml_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) пре 10 месеци
gguf.go 4a565cbf94 add chat and generate tests with mock runner пре 9 месеци
llm.go 10e768826c fix: quant err message (#5616) пре 9 месеци
llm_darwin_amd64.go 58d95cc9bd Switch back to subprocessing for llama.cpp пре 1 година
llm_darwin_arm64.go 58d95cc9bd Switch back to subprocessing for llama.cpp пре 1 година
llm_linux.go 58d95cc9bd Switch back to subprocessing for llama.cpp пре 1 година
llm_windows.go 058f6cd2cc Move nested payloads to installer and zip file on windows пре 1 година
memory.go 8e0641a9bf handle asymmetric embedding KVs пре 10 месеци
memory_test.go cb42e607c5 llm: speed up gguf decoding by a lot (#5246) пре 10 месеци
payload.go 0e982bc1f4 Fix corner cases on tmp cleaner on mac пре 10 месеци
server.go a3c20e3f18 Refine error reporting for subprocess crash пре 9 месеци
status.go 4d71c559b2 fix error detection by limiting model loading error parsing (#5472) пре 10 месеци