ik_llama.cpp.git - Unnamed repository; edit this file 'description' to name the repository.

Age	Commit message (Expand)	Author
2023-08-29	10X faster BPE tokenizer (#2876)	Kawrakow
2023-08-28	train : mem usage and other improvements (#2439)	xaedes
2023-08-28	YAML result logging + preset script (#2657)	Johannes Gäßler
2023-08-28	llama.cpp : fix wrong vsnprintf call in MS compiler (#2856)	grahameth
2023-08-27	llama : fix MPI threads (close #2827)	Georgi Gerganov
2023-08-27	llama : speedup tokenization (#2831)	Kawrakow
2023-08-27	falcon : fix CUDA inference by making K and Q contiguous (#2830)	Georgi Gerganov
2023-08-27	k_quants tuning for Falcon-7b (#2816)	Kawrakow
2023-08-27	gguf : add 64-bit support (GGUF v2) (#2821)	Georgi Gerganov
2023-08-27	llama : more tokenizer fixes (#2810)	Georgi Gerganov
2023-08-27	ggml : detect SSSE3 (#2825)	Przemysław Pawełczyk
2023-08-26	llama : use Unicode Escape Sequence to replace encoded characters (#2814)	Tim Miller
2023-08-26	llama : move #includes out of _GNU_SOURCE conditional (#2817)	Cebtenzzre
2023-08-26	llama : use std::abs in llama_sample_tail_free (#2800)	Cebtenzzre
2023-08-26	k-quants : remove unnecessary tensor shape restrictions (#2811)	Georgi Gerganov
2023-08-26	Better perplexity for 2- and 3-bit quantization for LLaMA-v2-70B (#2807)	Kawrakow
2023-08-26	Fix spm whitespaces (#2806)	klosax
2023-08-25	llama : add llama_beam_search() (#2267)	Matt Pulver
2023-08-25	llama-bench : add model sizes (#2771)	slaren
2023-08-25	ROCm Port (#1087)	Henri Vasserman
2023-08-25	cuda : add RoPE kernel for mode == 2 (NeoX) (#2760)	Georgi Gerganov
2023-08-24	gguf : add rope_freq_base parameter for CodeLlama (#2769)	slaren
2023-08-24	metal : bug-fix when enable ggml-alloc (#2757)	Shouzheng Liu
2023-08-24	fix convert.py for codellama, add llama 34B to the list of recognized models ...	slaren
2023-08-24	llama : escape all U+2581 in a string (#2750)	Georgi Gerganov
2023-08-24	llama : fix grammar sometimes generating null char (#2756)	Evan Jones
2023-08-23	llm : add Falcon support (#2717)	Georgi Gerganov
2023-08-22	Improve handling of special tokens in GGML to GGUF converter (#2725)	Kerfuffle
2023-08-23	llama : fix whitespace escaping in tokenizer (#2724)	goerch
2023-08-22	gguf : add ftype meta info to the model (#2710)	Georgi Gerganov
2023-08-22	Quantization imrovements for k_quants (#2707)	Kawrakow
2023-08-22	ggml-cuda : use graph allocator (#2684)	slaren
2023-08-21	gguf : new file format with flexible meta data (beta) (#2398)	Georgi Gerganov
2023-08-18	llama : add benchmark example (#2626)	slaren
2023-08-17	Fix unicode in grammars (fixes #2501) (#2553)	Evan Jones
2023-08-17	llama : replace (permute + reshape + view_1d) with (view_3d) (#2538)	Georgi Gerganov
2023-08-16	metal : enable ggml-alloc (#2627)	Shouzheng Liu
2023-08-16	metal : matrix-matrix multiplication kernel (#2615)	Shouzheng Liu
2023-08-14	metal : return null instead of exit(1) (#2573)	Jhen-Jie Hong
2023-08-09	add log_callback to llama_context_params for custom logging. (#2234)	grahameth
2023-08-08	CUDA: tighter VRAM scratch size for 65b/70b (#2551)	Johannes Gäßler
2023-08-07	Fixed mmap prefetch for GPU offloading (#2529)	Johannes Gäßler
2023-08-04	Stream save llama context data to file instead of allocating entire buffer up...	l3utterfly
2023-07-31	CUDA: mmq CLI option, fixed mmq build issues (#2453)	Johannes Gäßler
2023-07-31	Fix Metal backend broken from the allocator changes (#2455)	slaren
2023-07-30	ggml : add graph tensor allocator (#2411)	slaren
2023-07-28	llama : support more diverse tokenizers? (#2420)	eric8607242
2023-07-28	llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)	Rand Xie
2023-07-27	metal : disable graph concurrency optimization due to bug (#2413)	Georgi Gerganov
2023-07-26	ggml : allocate graphs in a context (#2392)	slaren