llama.cpp.git - llama.cpp

Age	Commit message (Expand)	Author
2023-07-10	mpi : add support for distributed inference via MPI (#2099)	Evan Miller
2023-07-09	llama : remove "first token must be BOS" restriction (#2153)	oobabooga
2023-07-09	main : escape prompt prefix/suffix (#2151)	Nigel Bosch
2023-07-09	readme : update Termux instructions (#2147)	JackJollimore
2023-07-09	ggml : fix buidling with Intel MKL but ask for "cblas.h" issue (#2104) (#2115)	clyang
2023-07-09	readme : add more docs indexes (#2127)	rankaiyx
2023-07-08	Fixed OpenLLaMA 3b CUDA mul_mat_vec_q (#2144)	Johannes Gäßler
2023-07-08	CUDA: add __restrict__ to mul mat vec kernels (#2140)	Johannes Gäßler
2023-07-07	docker : add support for CUDA in docker (#1461)	dylan
2023-07-07	ci : switch threads to 1 (#2138)	Georgi Gerganov
2023-07-07	ggml : change ggml_graph_compute() API to not require context (#1999)	Qingyou Meng
2023-07-07	ggml : remove sched_yield() call in ggml_graph_compute_thread() (#2134)	Georgi Gerganov
2023-07-07	convert.py: add mapping for safetensors bf16 (#1598)	Aarni Koskela
2023-07-07	Fix opencl by wrap #if-else-endif with \n (#2086)	Howard Su
2023-07-06	ggml : fix restrict usage	Georgi Gerganov
2023-07-06	convert : update for baichuan (#2081)	Judd
2023-07-06	alpaca.sh : update model file name (#2074)	tslmy
2023-07-05	Expose generation timings from server & update completions.js (#2116)	Tobias Lütke
2023-07-05	Update Server Instructions (#2113)	Jesse Jojo Johnson
2023-07-05	ggml : fix bug introduced in #1237	Georgi Gerganov
2023-07-05	tests : fix test-grad0	Georgi Gerganov
2023-07-05	ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)	Stephan Walter
2023-07-05	Update server instructions for web front end (#2103)	Jesse Jojo Johnson
2023-07-05	Quantized dot products for CUDA mul mat vec (#2067)	Johannes Gäßler
2023-07-05	llama: Don't double count the sampling time (#2107)	Howard Su
2023-07-05	Fixed OpenCL offloading prints (#2082)	Johannes Gäßler
2023-07-05	embd-input: Fix input embedding example unsigned int seed (#2105)	Nigel Bosch
2023-07-04	readme : add link web chat PR	Georgi Gerganov
2023-07-04	ggml : sync latest (new ops, macros, refactoring) (#2106)	Georgi Gerganov
2023-07-04	Add an API example using server.cpp similar to OAI. (#2009)	jwj7140
2023-07-04	Simple webchat for server (#1998)	Tobias Lütke
2023-07-04	Allow old Make to build server. (#2098)	Henri Vasserman
2023-07-04	Update Makefile: clean simple (#2097)	ZhouYuChen
2023-07-04	CI: make the brew update temporarily optional. (#2092)	Erik Scholz
2023-07-04	[ggml] fix index for ne03 value in ggml_cl_mul_f32 (#2088)	Govlzkoy
2023-07-04	fix server crashes (#2076)	Henri Vasserman
2023-07-03	Fix crash of test-tokenizer-0 under Debug build (#2064)	Howard Su
2023-07-03	[llama] No need to check file version when loading vocab score (#2079)	Howard Su
2023-07-03	server: add option to output probabilities for completion (#1962)	WangHaoranRobin
2023-07-02	ggml : fix build with OpenBLAS (close #2066)	Georgi Gerganov
2023-07-01	Better CUDA synchronization logic (#2057)	Johannes Gäßler
2023-07-01	Test-based VRAM scratch size + context adjustment (#2056)	Johannes Gäßler
2023-07-01	cmake : don't force -mcpu=native on aarch64 (#2063)	Daniel Drake
2023-07-01	metal : release buffers when freeing metal context (#2062)	Aaron Miller
2023-07-01	convert : add support of baichuan-7b (#2055)	Judd
2023-07-01	llama : fix return value of llama_load_session_file_internal (#2022)	Georgi Gerganov
2023-07-01	llama : catch llama_load_session_file_internal exceptions (#2022)	Rand Xie
2023-07-01	embd-input : fix returning ptr to temporary	Georgi Gerganov
2023-07-01	train : fix compile warning	Georgi Gerganov
2023-07-01	ggml : disable GGML_TASK_INIT and GGML_TASK_FINALIZE by default (#1995)	Qingyou Meng