git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog

overview / pkg / ggml / sources / llama.cpp / shortlog

2023-06-19	Georgi Gerganov	cmake : fix trailing whitespaces	commit \| commitdiff \| tree
2023-06-19	Kawrakow	llama : only use Q6_K for output weights if tensor...	commit \| commitdiff \| tree
2023-06-19	Kawrakow	cuda : faster k-quants on older GPUs (#1930)	commit \| commitdiff \| tree
2023-06-19	Georgi Gerganov	ggml : sync latest ggml repo (#1924)	commit \| commitdiff \| tree
2023-06-19	Howard Su	cmake : fix build shared ggml when CUDA is enabled...	commit \| commitdiff \| tree
2023-06-19	Johannes Gäßler	Convert vector to f16 for dequantize mul mat vec (...	commit \| commitdiff \| tree
2023-06-18	Johannes Gäßler	Added tokens per second to info prints (#1928)	commit \| commitdiff \| tree
2023-06-18	Johannes Gäßler	Fixed incorrectly applying RMS norm twice (#1925)	commit \| commitdiff \| tree
2023-06-18	l3utterfly	ggml : fix bug in ggml_compute_forward_add_q_f32 (...	commit \| commitdiff \| tree
2023-06-18	Mike	readme : update Android build instructions (#1922)	commit \| commitdiff \| tree
2023-06-18	Kawrakow	llama : prevent usage of k-quants when tensor size...	commit \| commitdiff \| tree
2023-06-18	Kawrakow	examples : fix examples/metal (#1920)	commit \| commitdiff \| tree
2023-06-18	Georgi Gerganov	metal : handle buffers larger than device's maxBufferLe...	commit \| commitdiff \| tree
2023-06-18	Howard Su	cmake : add CUDA_ARCHITECTURES to new target ggml_stati...	commit \| commitdiff \| tree
2023-06-17	Georgi Gerganov	make : do not print help for simple example	commit \| commitdiff \| tree
2023-06-17	Georgi Gerganov	minor : warning fixes	commit \| commitdiff \| tree
2023-06-17	Johannes Gäßler	Only one CUDA stream per device for async compute ...	commit \| commitdiff \| tree
2023-06-17	Georgi Gerganov	llama : fix kv_cache `n` init (close #1903)	commit \| commitdiff \| tree
2023-06-17	DaniAndTheWeb	make : update for latest Arch (#1701)	commit \| commitdiff \| tree
2023-06-17	Howard Su	ggml : fix warnings under MSVC (#1908)	commit \| commitdiff \| tree
2023-06-17	Aaron Miller	metal : add norm, cpy f16->f16, alibi kernels (#1823)	commit \| commitdiff \| tree
2023-06-17	Faez Shakil	exposed modules so that they can be invoked by nix...	commit \| commitdiff \| tree
2023-06-17	Randall Fitzgerald	Server Example Refactor and Improvements (#1570)	commit \| commitdiff \| tree
2023-06-17	Jiří Podivín	hooks : setting up flake8 and pre-commit hooks (#1681)	commit \| commitdiff \| tree
2023-06-17	Gustavo Rocha...	readme : alternative way to build for Android with...	commit \| commitdiff \| tree
2023-06-17	Kerfuffle	Allow cmake to build ggml as a library (#1896)	commit \| commitdiff \| tree
2023-06-17	David Yang	train : get raw text instead of page with html (#1905)	commit \| commitdiff \| tree
2023-06-16	0cc4m	opencl : support k-quants (#1836)	commit \| commitdiff \| tree
2023-06-16	SuperUserNameMan	examples : add "simple" (#1840)	commit \| commitdiff \| tree
2023-06-16	Zenix	cmake : add auto detection of BLAS_INCLUDE_DIRS (#1886)	commit \| commitdiff \| tree
2023-06-16	Johannes Gäßler	llama : fix embd when offloading non-repeating layers...	commit \| commitdiff \| tree
2023-06-16	FrankHB	Fixed possible macro redefinition (#1892)	commit \| commitdiff \| tree
2023-06-16	Borislav Stanimirov	build : fix and ignore MSVC warnings (#1889)	commit \| commitdiff \| tree
2023-06-16	Kawrakow	CUDA : faster k-quant dot kernels (#1862)	commit \| commitdiff \| tree
2023-06-16	Borislav Stanimirov	gitignore : add several entries specific to Visual...	commit \| commitdiff \| tree
2023-06-15	Johannes Gäßler	Fixed CUDA runtime version check (#1879)	commit \| commitdiff \| tree
2023-06-15	Georgi Gerganov	cmake : remove whitespaces	commit \| commitdiff \| tree
2023-06-15	yangli2	examples : add chat-vicuna.sh (#1854)	commit \| commitdiff \| tree
2023-06-15	Igor Okulist	cmake : set include path for OpenBlas (#1830)	commit \| commitdiff \| tree
2023-06-15	Frederik Vogel	swift : Package compile breaks due to ggml-metal.metal...	commit \| commitdiff \| tree
2023-06-15	daboe01	make : add train-text-from-scratch (#1850)	commit \| commitdiff \| tree
2023-06-15	Srinivas Billa	readme : server compile flag (#1874)	commit \| commitdiff \| tree
2023-06-15	sandyiscool	make : clean *.so files (#1857)	commit \| commitdiff \| tree
2023-06-15	Howard Su	Fix the validation of main device (#1872)	commit \| commitdiff \| tree
2023-06-15	Georgi Gerganov	metal : parallel command buffer encoding (#1860)	commit \| commitdiff \| tree
2023-06-15	Johannes Gäßler	Better error when using both LoRA + GPU layers (#1861)	commit \| commitdiff \| tree
2023-06-14	Johannes Gäßler	CUDA full GPU acceleration, KV cache in VRAM (#1827)	commit \| commitdiff \| tree
2023-06-13	0xspringtime	baby-llama : fix operator!= (#1821)	commit \| commitdiff \| tree
2023-06-13	xaedes	train : improved training-from-scratch example (#1652)	commit \| commitdiff \| tree
2023-06-13	Georgi Gerganov	llama : do a warm-up eval at start for better timings...	commit \| commitdiff \| tree
2023-06-13	Kerfuffle	Allow "quantizing" to f16 and f32 (#1787)	commit \| commitdiff \| tree
2023-06-12	Kawrakow	Metal implementation for all k_quants (#1807)	commit \| commitdiff \| tree
2023-06-12	slaren	ci : run when changing only the CUDA sources (#1800)	commit \| commitdiff \| tree
2023-06-12	Howard Su	Leverage mmap for offloading tensors to GPU (#1597)	commit \| commitdiff \| tree
2023-06-12	Kawrakow	metal : fix failure to load model (#1817)	commit \| commitdiff \| tree
2023-06-11	Kerfuffle	Fix issue where interactive mode crashes when input...	commit \| commitdiff \| tree
2023-06-11	Kyle Liang	Fixed WSL cuda's OOM error (#1594)	commit \| commitdiff \| tree
2023-06-11	Ryan Landay	Update SHA256SUMS with current hashes for models quanti...	commit \| commitdiff \| tree
2023-06-10	Georgi Gerganov	cmake : fix Metal build (close #1791)	commit \| commitdiff \| tree
2023-06-10	Artyom Lebedev	k-quants : GCC12 compilation fix (#1792)	commit \| commitdiff \| tree
2023-06-10	Andrei	metal : fix issue with ggml-metal.metal path. Closes...	commit \| commitdiff \| tree
2023-06-10	Aisuko	doc : fix wrong address of BLIS.md (#1772)	commit \| commitdiff \| tree
2023-06-10	Georgi Gerganov	ggml : force no_alloc == false when creating opt tensor...	commit \| commitdiff \| tree
2023-06-10	Kawrakow	metal : add Q4_1 implementation (#1785)	commit \| commitdiff \| tree
2023-06-10	Kerfuffle	llama : support requantizing models instead of only...	commit \| commitdiff \| tree
2023-06-10	Xingchen Song...	ggml : workaround for missing _mm256_setr_m128i in...	commit \| commitdiff \| tree
2023-06-10	rankaiyx	make : add SSSE3 compilation use case (#1659)	commit \| commitdiff \| tree
2023-06-09	Robert Sung...	OpenCL: Add release memory (#1741)	commit \| commitdiff \| tree
2023-06-09	Johannes Gäßler	Windows nvcc workaround (#1753)	commit \| commitdiff \| tree
2023-06-09	Georgi Gerganov	metal : fix build "tanhf" -> "tanh"	commit \| commitdiff \| tree
2023-06-09	AT	metal : add GELU implementation (#1770)	commit \| commitdiff \| tree
2023-06-09	Kawrakow	metal : faster q4_0 (#1775)	commit \| commitdiff \| tree
2023-06-08	Kawrakow	metal : add Q2_K implementation (#1762)	commit \| commitdiff \| tree
2023-06-08	Georgi Gerganov	Revert "ggml : load data into int8x16x4_t using vld4q_s...	commit \| commitdiff \| tree
2023-06-08	le.chang	ggml : load data into int8x16x4_t using vld4q_s8 on...	commit \| commitdiff \| tree
2023-06-08	Kawrakow	metal : Q6_K implementation (#1752)	commit \| commitdiff \| tree
2023-06-08	qingfengfenga	Add llama.cpp docker support for non-latin languages...	commit \| commitdiff \| tree
2023-06-08	Steven Roussey	ggml : fix fprintf warnings (#1720)	commit \| commitdiff \| tree
2023-06-08	Georgi Gerganov	clang-tidy : restore dot file from accidental deletion	commit \| commitdiff \| tree
2023-06-08	Kawrakow	metal : add Q4_K implementation (#1733)	commit \| commitdiff \| tree
2023-06-08	johnson442	k-quants : add missing compile definition to CMakeLists...	commit \| commitdiff \| tree
2023-06-07	Georgi Gerganov	k-quants : allow to optionally disable at compile time...	commit \| commitdiff \| tree
2023-06-07	jacobi petrucciani	flake : update to support metal on m1/m2 (#1724)	commit \| commitdiff \| tree
2023-06-07	Georgi Gerganov	readme : add June roadmap	commit \| commitdiff \| tree
2023-06-07	Willy Tarreau	main: add the possibility to open the prompt cache...	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	llama : fix vram_scratch var	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	llama : fix compile warnings	commit \| commitdiff \| tree
2023-06-06	Johannes Gäßler	Multi GPU support, CUDA refactor, CUDA scratch buffer...	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	metal : add f16 support	commit \| commitdiff \| tree
2023-06-06	LostRuins	Clblast fixes + enhancements to save VRAM and offload...	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	ggml : fix builds, add ggml-quants-k.o (close #1712...	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	gitignore : add .clang-tidy	commit \| commitdiff \| tree
2023-06-06	Georgi Gerganov	llama : temporary disable Q6_K output quantization...	commit \| commitdiff \| tree
2023-06-06	Spencer Sutton	metal : add checks for buffer size (#1706)	commit \| commitdiff \| tree
2023-06-05	Yuval Peled	docs : add performance troubleshoot + example benchmark...	commit \| commitdiff \| tree
2023-06-05	Foul-Tarnished	readme : fix typo (#1700)	commit \| commitdiff \| tree
2023-06-05	mgroeber9110	llama : consistently catch and throw only exceptions...	commit \| commitdiff \| tree
2023-06-05	kiltyj	metal : use shared buffers between CPU and GPU (#1696)	commit \| commitdiff \| tree
2023-06-05	grahameth	ggml : fix internal overflow in ggml_time_us on Windows...	commit \| commitdiff \| tree
2023-06-05	Georgi Gerganov	ci : disable auto tidy (#1705)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom