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

2023-06-28	Johannes Gäßler	CUDA GPU acceleration for LoRAs + f16 models (#1970)	commit \| commitdiff \| tree
2023-06-28	ningshanwutuobang	llama : support input embeddings directly (#1910)	commit \| commitdiff \| tree
2023-06-27	Erik Scholz	fix pthreads setaffinity usage on android (#2020)	commit \| commitdiff \| tree
2023-06-27	Howard Su	baby-llama : fix build after ggml_rope change (#2016)	commit \| commitdiff \| tree
2023-06-26	Georgi Gerganov	llama : fix rope usage after ChatGLM change	commit \| commitdiff \| tree
2023-06-26	Georgi Gerganov	ggml : add support for ChatGLM RoPE	commit \| commitdiff \| tree
2023-06-26	Roman Parykin	readme : add Scala 3 bindings repo (#2010)	commit \| commitdiff \| tree
2023-06-26	David Yang	ggml : increase max tensor name + clean up compiler...	commit \| commitdiff \| tree
2023-06-26	Gustavo Rocha...	readme : LD_LIBRARY_PATH complement for some Android...	commit \| commitdiff \| tree
2023-06-26	Georgi Gerganov	ggml : avoid conv 2d kernel round up	commit \| commitdiff \| tree
2023-06-26	zrm	ggml : add NUMA support (#1556)	commit \| commitdiff \| tree
2023-06-26	Georgi Gerganov	k-quants : fix indentation	commit \| commitdiff \| tree
2023-06-26	katsu560	tests : fix quantize perf (#1990)	commit \| commitdiff \| tree
2023-06-26	katsu560	k-quants : add AVX support to dot functions (#1916)	commit \| commitdiff \| tree
2023-06-26	Georgi Gerganov	readme : add link to new k-quants for visibility	commit \| commitdiff \| tree
2023-06-26	Kawrakow	k-quants : support for super-block size of 64 (#2001)	commit \| commitdiff \| tree
2023-06-26	Howard Su	Fix assert when free invalid cuda pointer (#2005)	commit \| commitdiff \| tree
2023-06-25	Georgi Gerganov	readme : add new roadmap + manifesto	commit \| commitdiff \| tree
2023-06-25	Georgi Gerganov	ggml : sync latest ggml (custom operators)	commit \| commitdiff \| tree
2023-06-25	anon998	fix server sampling: top k sampler first (#1977)	commit \| commitdiff \| tree
2023-06-25	Georgi Gerganov	readme : add Azure CI discussion link	commit \| commitdiff \| tree
2023-06-25	sjinzh	zig : upgrade build system support (#1981)	commit \| commitdiff \| tree
2023-06-24	Robyn	#1869 Fix null reference errors when training from...	commit \| commitdiff \| tree
2023-06-24	Georgi Gerganov	tests : sync test-grad0 from ggml	commit \| commitdiff \| tree
2023-06-24	Rowan Hart	flake : fix ggml-metal.metal path and run nixfmt (...	commit \| commitdiff \| tree
2023-06-24	AN Long	convert : fix invalid params in write_vocab_only (...	commit \| commitdiff \| tree
2023-06-24	slaren	ggml : improve ggml_graph_dump_dot, add ggml_format_nam...	commit \| commitdiff \| tree
2023-06-24	Georgi Gerganov	readme : fix whitespaces	commit \| commitdiff \| tree
2023-06-24	Alberto	readme : fixed termux instructions (#1973)	commit \| commitdiff \| tree
2023-06-24	Alex Renda	llama : fix top-p sampling to match the canonical defin...	commit \| commitdiff \| tree
2023-06-24	Didzis Gosko	llama : make model stateless and context stateful ...	commit \| commitdiff \| tree
2023-06-23	eiery	Add OpenLLaMA instructions to the README (#1954)	commit \| commitdiff \| tree
2023-06-22	Erik Scholz	rework convert.py to read hyper-parameters from config...	commit \| commitdiff \| tree
2023-06-21	Johannes Gäßler	cmake: revert CUDA arch default to 52, 61 if f16 (...	commit \| commitdiff \| tree
2023-06-21	Rahul Vivek...	Fix typo in README.md (#1961)	commit \| commitdiff \| tree
2023-06-20	Georgi Gerganov	readme : add link to p1	commit \| commitdiff \| tree
2023-06-20	Xiake Sun	Fix typo (#1949)	commit \| commitdiff \| tree
2023-06-20	Ettore Di Giacinto	llama : fix params struct slignment (#1936)	commit \| commitdiff \| tree
2023-06-19	Henri Vasserman	[Fix] Reenable server embedding endpoint (#1937)	commit \| commitdiff \| tree
2023-06-19	Georgi Gerganov	ggml : fix bug in LBFGS optimizer (found by ggml tests)	commit \| commitdiff \| tree
2023-06-19	l3utterfly	llama : use aligned memory during ggml_init call from...	commit \| commitdiff \| tree
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
next

Packaging of ggml-org/llama.cpp

RSS Atom