llama.cpp.git - llama.cpp

Age	Commit message (Expand)	Author
2023-07-11	llama : add classifier-free guidance (#2135)	Bach Le
2023-07-11	Possible solution to allow K-quants on models with n_vocab!=32000 (#2148)	LostRuins
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
2023-07-07	ggml : change ggml_graph_compute() API to not require context (#1999)	Qingyou Meng
2023-07-05	Expose generation timings from server & update completions.js (#2116)	Tobias Lütke
2023-07-05	ggml : generalize `quantize_fns` for simpler FP16 handling (#1237)	Stephan Walter
2023-07-05	llama: Don't double count the sampling time (#2107)	Howard Su
2023-07-05	Fixed OpenCL offloading prints (#2082)	Johannes Gäßler
2023-07-03	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
2023-07-01	Test-based VRAM scratch size + context adjustment (#2056)	Johannes Gäßler
2023-07-01	metal : release buffers when freeing metal context (#2062)	Aaron Miller
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
2023-06-29	Use unsigned for random seed (#2006)	Howard Su
2023-06-28	llama : replacing auto &kv with const auto &kv (#2041)	m3ndax
2023-06-28	llama : remove shards weight file support (#2000)	Howard Su
2023-06-28	CUDA GPU acceleration for LoRAs + f16 models (#1970)	Johannes Gäßler
2023-06-28	llama : support input embeddings directly (#1910)	ningshanwutuobang
2023-06-27	llama : fix rope usage after ChatGLM change	Georgi Gerganov
2023-06-26	ggml : add NUMA support (#1556)	zrm
2023-06-26	k-quants : support for super-block size of 64 (#2001)	Kawrakow
2023-06-24	llama : fix top-p sampling to match the canonical definition (#1953)	Alex Renda
2023-06-24	llama : make model stateless and context stateful (llama_state) (#1797)	Didzis Gosko
2023-06-20	llama : fix params struct slignment (#1936)	Ettore Di Giacinto
2023-06-19	llama : use aligned memory during ggml_init call from loading saved sessions ...	l3utterfly
2023-06-19	llama : only use Q6_K for output weights if tensor size is multiple of 256 (#...	Kawrakow
2023-06-19	Convert vector to f16 for dequantize mul mat vec (#1913)	Johannes Gäßler
2023-06-18	Added tokens per second to info prints (#1928)	Johannes Gäßler
2023-06-18	Fixed incorrectly applying RMS norm twice (#1925)	Johannes Gäßler
2023-06-18	llama : prevent usage of k-quants when tensor size is not a multiple of 256 (...	Kawrakow
2023-06-18	metal : handle buffers larger than device's maxBufferLength (#1826)	Georgi Gerganov
2023-06-17	llama : fix kv_cache `n` init (close #1903)	Georgi Gerganov
2023-06-17	ggml : fix warnings under MSVC (#1908)	Howard Su
2023-06-16	llama : fix embd when offloading non-repeating layers (#1891)	Johannes Gäßler
2023-06-16	build : fix and ignore MSVC warnings (#1889)	Borislav Stanimirov
2023-06-14	CUDA full GPU acceleration, KV cache in VRAM (#1827)	Johannes Gäßler
2023-06-13	train : improved training-from-scratch example (#1652)	xaedes
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	Leverage mmap for offloading tensors to GPU (#1597)	Howard Su
2023-06-10	llama : support requantizing models instead of only allowing quantization fro...	Kerfuffle
2023-06-09	OpenCL: Add release memory (#1741)	Robert Sung-wook Shin
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	llama : temporary disable Q6_K output quantization (#1711)	Georgi Gerganov
2023-06-06	metal : add checks for buffer size (#1706)	Spencer Sutton