llama.cpp.git - llama.cpp

Age	Commit message (Expand)	Author
2023-06-13	baby-llama : fix operator!= (#1821)	0xspringtime
2023-06-13	train : improved training-from-scratch example (#1652)	xaedes
2023-06-13	llama : do a warm-up eval at start for better timings (#1824)	Georgi Gerganov
2023-06-13	Allow "quantizing" to f16 and f32 (#1787)	Kerfuffle
2023-06-12	Metal implementation for all k_quants (#1807)	Kawrakow
2023-06-12	ci : run when changing only the CUDA sources (#1800)	slaren
2023-06-12	Leverage mmap for offloading tensors to GPU (#1597)	Howard Su
2023-06-12	metal : fix failure to load model (#1817)	Kawrakow
2023-06-11	Fix issue where interactive mode crashes when input exceeds ctx size (#1789)	Kerfuffle
2023-06-11	Fixed WSL cuda's OOM error (#1594)	Kyle Liang
2023-06-11	Update SHA256SUMS with current hashes for models quantized using q4_0 (#1798)	Ryan Landay
2023-06-10	cmake : fix Metal build (close #1791)	Georgi Gerganov
2023-06-10	k-quants : GCC12 compilation fix (#1792)	Artyom Lebedev
2023-06-10	metal : fix issue with ggml-metal.metal path. Closes #1769 (#1782)	Andrei
2023-06-10	doc : fix wrong address of BLIS.md (#1772)	Aisuko
2023-06-10	ggml : force no_alloc == false when creating opt tensors (close #1699)	Georgi Gerganov
2023-06-10	metal : add Q4_1 implementation (#1785)	Kawrakow
2023-06-10	llama : support requantizing models instead of only allowing quantization fro...	Kerfuffle
2023-06-10	ggml : workaround for missing _mm256_setr_m128i in GCC < 8 (#1638)	Xingchen Song(宋星辰)
2023-06-10	make : add SSSE3 compilation use case (#1659)	rankaiyx
2023-06-09	OpenCL: Add release memory (#1741)	Robert Sung-wook Shin
2023-06-09	Windows nvcc workaround (#1753)	Johannes Gäßler
2023-06-09	metal : fix build "tanhf" -> "tanh"	Georgi Gerganov
2023-06-09	metal : add GELU implementation (#1770)	AT
2023-06-09	metal : faster q4_0 (#1775)	Kawrakow
2023-06-08	metal : add Q2_K implementation (#1762)	Kawrakow
2023-06-08	Revert "ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)"	Georgi Gerganov
2023-06-08	ggml : load data into int8x16x4_t using vld4q_s8 on arm64 (#1738)	le.chang
2023-06-08	metal : Q6_K implementation (#1752)	Kawrakow
2023-06-08	Add llama.cpp docker support for non-latin languages (#1673)	qingfengfenga
2023-06-08	ggml : fix fprintf warnings (#1720)	Steven Roussey
2023-06-08	clang-tidy : restore dot file from accidental deletion	Georgi Gerganov
2023-06-08	metal : add Q4_K implementation (#1733)	Kawrakow
2023-06-08	k-quants : add missing compile definition to CMakeLists (#1748)	johnson442
2023-06-07	k-quants : allow to optionally disable at compile time (#1734)	Georgi Gerganov
2023-06-07	flake : update to support metal on m1/m2 (#1724)	jacobi petrucciani
2023-06-07	readme : add June roadmap	Georgi Gerganov
2023-06-06	main: add the possibility to open the prompt cache read-only (#1640)	Willy Tarreau
2023-06-06	llama : fix vram_scratch var	Georgi Gerganov
2023-06-06	llama : fix compile warnings	Georgi Gerganov
2023-06-06	Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)	Johannes Gäßler
2023-06-06	metal : add f16 support	Georgi Gerganov
2023-06-06	Clblast fixes + enhancements to save VRAM and offload more layers (#1675)	LostRuins
2023-06-06	ggml : fix builds, add ggml-quants-k.o (close #1712, close #1710)	Georgi Gerganov
2023-06-06	gitignore : add .clang-tidy	Georgi Gerganov
2023-06-06	llama : temporary disable Q6_K output quantization (#1711)	Georgi Gerganov
2023-06-06	metal : add checks for buffer size (#1706)	Spencer Sutton
2023-06-05	docs : add performance troubleshoot + example benchmark documentation (#1674)	Yuval Peled
2023-06-05	readme : fix typo (#1700)	Foul-Tarnished
2023-06-05	llama : consistently catch and throw only exceptions deriving from std::excep...	mgroeber9110