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

2023-07-11	LostRuins	Possible solution to allow K-quants on models with...	commit \| commitdiff \| tree
2023-07-10	Evan Miller	mpi : add support for distributed inference via MPI...	commit \| commitdiff \| tree
2023-07-09	oobabooga	llama : remove "first token must be BOS" restriction...	commit \| commitdiff \| tree
2023-07-09	Nigel Bosch	main : escape prompt prefix/suffix (#2151)	commit \| commitdiff \| tree
2023-07-09	JackJollimore	readme : update Termux instructions (#2147)	commit \| commitdiff \| tree
2023-07-09	clyang	ggml : fix buidling with Intel MKL but ask for "cblas...	commit \| commitdiff \| tree
2023-07-09	rankaiyx	readme : add more docs indexes (#2127)	commit \| commitdiff \| tree
2023-07-08	Johannes Gäßler	Fixed OpenLLaMA 3b CUDA mul_mat_vec_q (#2144)	commit \| commitdiff \| tree
2023-07-07	Johannes Gäßler	CUDA: add __restrict__ to mul mat vec kernels (#2140)	commit \| commitdiff \| tree
2023-07-07	dylan	docker : add support for CUDA in docker (#1461)	commit \| commitdiff \| tree
2023-07-07	Georgi Gerganov	ci : switch threads to 1 (#2138)	commit \| commitdiff \| tree
2023-07-07	Qingyou Meng	ggml : change ggml_graph_compute() API to not require...	commit \| commitdiff \| tree
2023-07-07	Georgi Gerganov	ggml : remove sched_yield() call in ggml_graph_compute_...	commit \| commitdiff \| tree
2023-07-07	Aarni Koskela	convert.py: add mapping for safetensors bf16 (#1598)	commit \| commitdiff \| tree
2023-07-07	Howard Su	Fix opencl by wrap #if-else-endif with \n (#2086)	commit \| commitdiff \| tree
2023-07-06	Georgi Gerganov	ggml : fix restrict usage	commit \| commitdiff \| tree
2023-07-06	Judd	convert : update for baichuan (#2081)	commit \| commitdiff \| tree
2023-07-06	tslmy	alpaca.sh : update model file name (#2074)	commit \| commitdiff \| tree
2023-07-05	Tobias Lütke	Expose generation timings from server & update completi...	commit \| commitdiff \| tree
2023-07-05	Jesse Jojo...	Update Server Instructions (#2113)	commit \| commitdiff \| tree
2023-07-05	Georgi Gerganov	ggml : fix bug introduced in #1237	commit \| commitdiff \| tree
2023-07-05	Georgi Gerganov	tests : fix test-grad0	commit \| commitdiff \| tree
2023-07-05	Stephan Walter	ggml : generalize `quantize_fns` for simpler FP16 handl...	commit \| commitdiff \| tree
2023-07-05	Jesse Jojo...	Update server instructions for web front end (#2103)	commit \| commitdiff \| tree
2023-07-05	Johannes Gäßler	Quantized dot products for CUDA mul mat vec (#2067)	commit \| commitdiff \| tree
2023-07-05	Howard Su	llama: Don't double count the sampling time (#2107)	commit \| commitdiff \| tree
2023-07-05	Johannes Gäßler	Fixed OpenCL offloading prints (#2082)	commit \| commitdiff \| tree
2023-07-04	Nigel Bosch	embd-input: Fix input embedding example unsigned int...	commit \| commitdiff \| tree
2023-07-04	Georgi Gerganov	readme : add link web chat PR	commit \| commitdiff \| tree
2023-07-04	Georgi Gerganov	ggml : sync latest (new ops, macros, refactoring) ...	commit \| commitdiff \| tree
2023-07-04	jwj7140	Add an API example using server.cpp similar to OAI...	commit \| commitdiff \| tree
2023-07-04	Tobias Lütke	Simple webchat for server (#1998)	commit \| commitdiff \| tree
2023-07-04	Henri Vasserman	Allow old Make to build server. (#2098)	commit \| commitdiff \| tree
2023-07-04	ZhouYuChen	Update Makefile: clean simple (#2097)	commit \| commitdiff \| tree
2023-07-03	Erik Scholz	CI: make the brew update temporarily optional. (#2092)	commit \| commitdiff \| tree
2023-07-03	Govlzkoy	[ggml] fix index for ne03 value in ggml_cl_mul_f32...	commit \| commitdiff \| tree
2023-07-03	Henri Vasserman	fix server crashes (#2076)	commit \| commitdiff \| tree
2023-07-03	Howard Su	Fix crash of test-tokenizer-0 under Debug build (#2064)	commit \| commitdiff \| tree
2023-07-03	Howard Su	[llama] No need to check file version when loading...	commit \| commitdiff \| tree
2023-07-02	WangHaoranRobin	server: add option to output probabilities for completi...	commit \| commitdiff \| tree
2023-07-02	Georgi Gerganov	ggml : fix build with OpenBLAS (close #2066)	commit \| commitdiff \| tree
2023-07-01	Johannes Gäßler	Better CUDA synchronization logic (#2057)	commit \| commitdiff \| tree
2023-07-01	Johannes Gäßler	Test-based VRAM scratch size + context adjustment ...	commit \| commitdiff \| tree
2023-07-01	Daniel Drake	cmake : don't force -mcpu=native on aarch64 (#2063)	commit \| commitdiff \| tree
2023-07-01	Aaron Miller	metal : release buffers when freeing metal context...	commit \| commitdiff \| tree
2023-07-01	Judd	convert : add support of baichuan-7b (#2055)	commit \| commitdiff \| tree
2023-07-01	Georgi Gerganov	llama : fix return value of llama_load_session_file_int...	commit \| commitdiff \| tree
2023-07-01	Rand Xie	llama : catch llama_load_session_file_internal exceptio...	commit \| commitdiff \| tree
2023-07-01	Georgi Gerganov	embd-input : fix returning ptr to temporary	commit \| commitdiff \| tree
2023-07-01	Georgi Gerganov	train : fix compile warning	commit \| commitdiff \| tree
2023-07-01	Qingyou Meng	ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE...	commit \| commitdiff \| tree
2023-06-29	Howard Su	Use unsigned for random seed (#2006)	commit \| commitdiff \| tree
2023-06-29	LostRuins	Porting the improved K-Quant CUDA kernels to OpenCL...	commit \| commitdiff \| tree
2023-06-28	m3ndax	llama : replacing auto &kv with const auto &kv (#2041)	commit \| commitdiff \| tree
2023-06-28	Salvador E...	cuda : remove nchannels_x argument from mul_mat_vec_nc_...	commit \| commitdiff \| tree
2023-06-28	Salvador E...	cuda : fix missing const qualifier in casts (#2027)	commit \| commitdiff \| tree
2023-06-28	Howard Su	llama : remove shards weight file support (#2000)	commit \| commitdiff \| tree
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
next

Packaging of ggml-org/llama.cpp

RSS Atom