]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2023-08-27 slarenci : add LoRA test to CI (#2650)
2023-08-26 Bruce MacDonaldserver : add `/detokenize` endpoint (#2802)
2023-08-26 Kerfuffleconvert.py : advanced option (#2753)
2023-08-26 Tim Millerllama : use Unicode Escape Sequence to replace encoded...
2023-08-26 Tungsten842flake.nix : add rocm support and cleanup (#2808)
2023-08-26 Cebtenzzrellama : move #includes out of _GNU_SOURCE conditional...
2023-08-26 Dr. Tom Murphy... main : fix bug (penalize_nl=false doesn't work) + suppr...
2023-08-26 Cebtenzzrellama : use std::abs in llama_sample_tail_free (#2800)
2023-08-26 Georgi Gerganovk-quants : remove unnecessary tensor shape restrictions...
2023-08-26 KawrakowBetter perplexity for 2- and 3-bit quantization for...
2023-08-26 KawrakowFix HellaSwag (#2805)
2023-08-26 Volodymyr Vitvitskyiflake : build llama.cpp on Intel with nix (#2795)
2023-08-26 Nigel BoschHandle null rope scaling value (#2793)
2023-08-26 klosaxFix spm whitespaces (#2806)
2023-08-26 lonexamples : skip unnecessary external lib in server...
2023-08-25 Marcus Dunnllama : fix struct decl (#2790)
2023-08-25 KawrakowFaster perplexity computation (#2786)
2023-08-25 Matt Pulverllama : add llama_beam_search() (#2267)
2023-08-25 Nigel Boschconvert.py : Get rope scale from HuggingFace models...
2023-08-25 slarenllama-bench : add model sizes (#2771)
2023-08-25 slarenconvert.py : export rope freq_base when converting...
2023-08-25 Jhen-Jie Hongserver : display token probabilities in the UI (#2489)
2023-08-25 Georgi Gerganovci : pip install gguf in editable mode (#2782)
2023-08-25 M. Yusuf Sarıgözgguf : export objects to user code (#2780)
2023-08-25 Henri VassermanROCm Port (#1087)
2023-08-25 Georgi Gerganovcuda : add RoPE kernel for mode == 2 (NeoX) (#2760)
2023-08-25 M. Yusuf Sarıgözgguf : make gguf pip-installable
2023-08-25 Shouzheng Liuggml-alloc : enlarge size of parse_seq (#2776)
2023-08-24 Marcus DunnAdded `enum` to `llama_token_get_type` return type...
2023-08-24 slarenconvert.py : try to determine n_ctx automatically for...
2023-08-24 slarengguf : add rope_freq_base parameter for CodeLlama ...
2023-08-24 Georgi Gerganovfalcon : write file type
2023-08-24 Shouzheng Liumetal : bug-fix when enable ggml-alloc (#2757)
2023-08-24 Georgi Gerganovconvert : auto-determine model name based on dir +...
2023-08-24 KerfuffleFix for main example getting stuck when -n -2 and ...
2023-08-24 slarenfix convert.py for codellama, add llama 34B to the...
2023-08-24 DannyDaemonicTag release with build number (#2732)
2023-08-24 Georgi Gerganovmetal : add Q8_0 support (#2763)
2023-08-24 Georgi Gerganovllama : escape all U+2581 in a string (#2750)
2023-08-24 Evan Jonesllama : fix grammar sometimes generating null char...
2023-08-23 Georgi Gerganovreadme : fix link
2023-08-23 Georgi Gerganovminor : fix trailing whitespace
2023-08-23 Georgi Gerganovreadme : update hot topics
2023-08-23 Georgi Gerganovllm : add Falcon support (#2717)
2023-08-23 Georgi Gerganovminor : fix trailing whitespace
2023-08-23 Olivier Chafikexamples : restore the functionality to import llama2...
2023-08-23 slarenfix convert-lora-to-ggml.py (#2738)
2023-08-23 klosaxmain : insert bos if no tokens (#2727)
2023-08-23 akawrykowgitignore : fix for windows (#2729)
2023-08-23 Cebtenzzrechmod : make scripts executable (#2675)
2023-08-23 JohnnyBdevops : RPM Specs (#2723)
2023-08-23 KawrakowFix values shown in the quantize tool help (#2735)
2023-08-23 KawrakowStrided perplexity (#2714)
2023-08-23 IgnacioFDMFix ggml to gguf conversion on Windows (#2733)
2023-08-23 Xiao-Yong Jinserver : allow json array in prompt or content for...
2023-08-23 Evan Jonesdocs : add grammar docs (#2701)
2023-08-22 KerfuffleImprove handling of special tokens in GGML to GGUF...
2023-08-22 goerchllama : fix whitespace escaping in tokenizer (#2724)
2023-08-22 Johannes GäßlerCUDA: use mul_mat_q kernels by default (#2683)
2023-08-22 Alex Petencheaconvert.py : clarifying error message (#2718)
2023-08-22 Jiahao LiFix CUDA softmax by subtracting max value before exp...
2023-08-22 Georgi Gerganovgguf : add ftype meta info to the model (#2710)
2023-08-22 KawrakowQuantization imrovements for k_quants (#2707)
2023-08-22 slarenembedding : evaluate prompt in batches (#2713)
2023-08-22 slarenggml-cuda : use graph allocator (#2684)
2023-08-22 Georgi Gerganovggml : sync latest (SAM + SD operators, CUDA alibi...
2023-08-22 slarenllama-bench : minor fixes (#2695)
2023-08-22 Kylinggml : support CUDA's half type for aarch64(#1455)...
2023-08-22 Shouzheng Liumetal : add missing barriers for mul-mat (#2699)
2023-08-22 Jhen-Jie Hongserver : fallback to default if client param is null...
2023-08-22 KerfuffleFix convert-llama-ggmlv3-to-gguf.py vocab conversion...
2023-08-21 Georgi Gerganovpy : remove obsolete script
2023-08-21 Georgi Gerganovgguf : new file format with flexible meta data (beta...
2023-08-21 Shouzheng Liumetal : fix synchronization in new matrix multiplicatio...
2023-08-21 KawrakowHellaSwag: split token evaluation into batches if neede...
2023-08-20 slarenggml : move all type info to ggml_type_traits (#2663)
2023-08-20 KawrakowMore efficient Hellaswag implementation (#2677)
2023-08-18 Georgi Gerganovserver : better default prompt (#2646)
2023-08-18 Jhen-Jie Hongserver : update xxd usage for older versions compatibil...
2023-08-18 AdrianAdd link to clojure bindings to Readme. (#2659)
2023-08-18 Georgi Gerganovreadme : incoming BREAKING CHANGE
2023-08-18 slarenllama : add benchmark example (#2626)
2023-08-18 mdrokzreadme : add link to Rust bindings (#2656)
2023-08-18 Georgi Gerganovperplexity : more meaningful ETA number - 2 decimal...
2023-08-17 Evan JonesFix unicode in grammars (fixes #2501) (#2553)
2023-08-17 staviqserver : support for saving templates in browser LocalS...
2023-08-17 Johannes GäßlerREADME: fix LLAMA_CUDA_MMV_Y documentation (#2647)
2023-08-17 Henri Vasserman[Zig] Fixing Zig build and improvements (#2554)
2023-08-17 KerfuffleAdd --cfg-negative-prompt-file option for examples...
2023-08-17 Georgi Gerganovllama : replace (permute + reshape + view_1d) with...
2023-08-17 drbhtests : adds simple llama grammar tests (#2618)
2023-08-17 Shouzheng Liuggml-alloc : fix discrepency between measure&eval ...
2023-08-16 Kolen Cheungcmake : install ggml-meta.metal if LLAMA_METAL (#2449)
2023-08-16 Jhen-Jie Hongmetal : print error of load pipeline state (#2564)
2023-08-16 Shouzheng Liumetal : enable ggml-alloc (#2627)
2023-08-16 Shouzheng Liumetal : matrix-matrix multiplication kernel (#2615)
2023-08-15 Georgi Gerganovscripts : add helper script to get wikitext
2023-08-14 Jhen-Jie Hongserver : add missing /json-schema-to-grammar.mjs (...
2023-08-14 Jhen-Jie Hongmetal : return null instead of exit(1) (#2573)
2023-08-14 Cheng Shaoserver : add --numa support (#2524)
next