aboutsummaryrefslogtreecommitdiff
path: root/ggml.h
AgeCommit message (Expand)Author
2023-04-17Add LoRA support (#820)slaren
2023-04-17Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)Ivan Komarov
2023-04-15ggml : add Q8_0 quantization for intermediate results (#951)Georgi Gerganov
2023-04-14Expose type name from ggml (#970)Pavol Rusnak
2023-04-14ggml : add unary and binary map operations (#874)Kerfuffle
2023-04-13ggml : add GGML_DEFAULT_N_THREADSGeorgi Gerganov
2023-04-11Add enum llama_ftype, sync ggml_type to model files (#709)Stephan Walter
2023-04-10ggml : add ggml_cont() + optimize ggml_cpy() for contiguous dstGeorgi Gerganov
2023-04-10Rewrite loading code to try to satisfy everyone:comex
2023-04-08Add quantize-stats command for testing quantization (#728)unbounded
2023-04-05ggml, llama : avoid heavy V transpose + improvements (#775)Georgi Gerganov
2023-04-02ggml : change ne to int64_t (#626)Marian Cepok
2023-03-30Ensure --mlock works properly with mmap() supportJustine Tunney
2023-03-30Add mmap support for model filesSlaren
2023-03-28ggml : introduce structs for the q4 data blocks (#356)Stephan Walter
2023-03-24Support calling mlock() on loaded model data on Linux and macOS (#453)comex
2023-03-22Deduplicate q4 quantization functions (#383)Stephan Walter
2023-03-22Introduce C-style API (#370)Georgi Gerganov
2023-03-16Add RMS norm and use it (#187)hoangmit
2023-03-10Initial releaseGeorgi Gerganov