summaryrefslogtreecommitdiff
path: root/llama.cpp
AgeCommit message (Expand)Author
2023-09-27gguf : fix a few general keys (#3341)Cebtenzzre
2023-09-27metal : reusing llama.cpp logging (#3152)Rickard Hallerbäck
2023-09-21CUDA: use only 1 thread if fully offloaded (#2915)Johannes Gäßler
2023-09-20llama : allow gguf RoPE keys to be overridden with defaults (#3240)Cebtenzzre
2023-09-17llama.cpp : show model size and BPW on load (#3223)slaren
2023-09-16Fixing the last deviations from sentencepiece indicated by test-tokenizer-1 (...goerch
2023-09-15check C++ code with -Wmissing-declarations (#3184)Cebtenzzre
2023-09-15llama : add support for StarCoder model architectures (#3187)Meng Zhang
2023-09-15metal : relax conditions on fast matrix multiplication kernel (#3168)Georgi Gerganov
2023-09-14llama : make quantize example up to 2.7x faster (#3115)Cebtenzzre
2023-09-14feature : support Baichuan serial models (#3009)jameswu2014
2023-09-13whisper : tokenizer fix + re-enable tokenizer test for LLaMa (#3096)goerch
2023-09-08examples : make n_ctx warning work again (#3066)Cebtenzzre
2023-09-08build : do not use _GNU_SOURCE gratuitously (#2035)Przemysław Pawełczyk
2023-09-08enable CPU HBM (#2603)Kunshang Ji
2023-09-07fix some warnings from gcc and clang-tidy (#3038)Cebtenzzre
2023-09-07ggml : posixify madvise and pagesize (#3037)Przemysław Pawełczyk
2023-09-05llama : update logic for number of threads when using BLASGeorgi Gerganov
2023-09-05speculative : add grammar support (#2991)Georgi Gerganov
2023-09-04build : on Mac OS enable Metal by default (#2901)Georgi Gerganov
2023-09-03llama : fix bpe tokenize from byte (#2889)opparco
2023-09-03examples : fix gpt-neox (#2943)momonga
2023-09-01Allow quantize to only copy tensors, some other improvements (#2931)Kerfuffle
2023-09-01minor : add const qualifiers (#2853)m3ndax
2023-09-01build : fix most gcc and clang warnings (#2861)Cebtenzzre
2023-08-31@vxiiduu's fix for PrefetchVirtualMemory (#2930)DannyDaemonic
2023-08-30CUDA: mul_mat_q=true llama_context_params default (#2912)Johannes Gäßler
2023-08-2910X faster BPE tokenizer (#2876)Kawrakow
2023-08-28train : mem usage and other improvements (#2439)xaedes
2023-08-28YAML result logging + preset script (#2657)Johannes Gäßler
2023-08-28llama.cpp : fix wrong vsnprintf call in MS compiler (#2856)grahameth
2023-08-27llama : fix MPI threads (close #2827)Georgi Gerganov
2023-08-27llama : speedup tokenization (#2831)Kawrakow
2023-08-27falcon : fix CUDA inference by making K and Q contiguous (#2830)Georgi Gerganov
2023-08-27k_quants tuning for Falcon-7b (#2816)Kawrakow
2023-08-27gguf : add 64-bit support (GGUF v2) (#2821)Georgi Gerganov
2023-08-27llama : more tokenizer fixes (#2810)Georgi Gerganov
2023-08-27ggml : detect SSSE3 (#2825)Przemysław Pawełczyk
2023-08-26llama : use Unicode Escape Sequence to replace encoded characters (#2814)Tim Miller
2023-08-26llama : move #includes out of _GNU_SOURCE conditional (#2817)Cebtenzzre
2023-08-26llama : use std::abs in llama_sample_tail_free (#2800)Cebtenzzre
2023-08-26k-quants : remove unnecessary tensor shape restrictions (#2811)Georgi Gerganov
2023-08-26Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B (#2807)Kawrakow
2023-08-26Fix spm whitespaces (#2806)klosax
2023-08-25llama : add llama_beam_search() (#2267)Matt Pulver
2023-08-25llama-bench : add model sizes (#2771)slaren
2023-08-25ROCm Port (#1087)Henri Vasserman
2023-08-25cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)Georgi Gerganov
2023-08-24gguf : add rope_freq_base parameter for CodeLlama (#2769)slaren
2023-08-24metal : bug-fix when enable ggml-alloc (#2757)Shouzheng Liu
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-04 19:07:24 +0000