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

2023-08-11	Equim	server: fixed wrong variable name in timing json (...	commit \| commitdiff \| tree
2023-08-10	DannyDaemonic	Handle `ENABLE_VIRTUAL_TERMINAL_PROCESSING` more gracef...	commit \| commitdiff \| tree
2023-08-10	Christian Demsar	Add --n-predict -2 for stopping generation on full...	commit \| commitdiff \| tree
2023-08-10	Martin Krasser	Fix grammar-based sampling issue in server (#2566)	commit \| commitdiff \| tree
2023-08-09	Sam Spilsbury	ggml-alloc: Don't try to re-use buffers of external...	commit \| commitdiff \| tree
2023-08-09	grahameth	add log_callback to llama_context_params for custom...	commit \| commitdiff \| tree
2023-08-09	Johannes Gäßler	CUDA: tuned mul_mat_q kernels (#2546)	commit \| commitdiff \| tree
2023-08-08	Martin Krasser	Allow passing grammar to completion endpoint (#2532)	commit \| commitdiff \| tree
2023-08-08	Johannes Gäßler	CUDA: tighter VRAM scratch size for 65b/70b (#2551)	commit \| commitdiff \| tree
2023-08-08	chaihahaha	llm.vim : multiline autocompletion, get rid of "^@...	commit \| commitdiff \| tree
2023-08-08	Georgi Gerganov	vim : bring back simple llm.vim example	commit \| commitdiff \| tree
2023-08-08	AustinMroz	vim : streaming and more (#2495)	commit \| commitdiff \| tree
2023-08-07	klosax	Add --rope-scale parameter (#2544)	commit \| commitdiff \| tree
2023-08-07	Georgi Gerganov	ggml : mul mat tweaks (#2372)	commit \| commitdiff \| tree
2023-08-07	Georgi Gerganov	ggml : pad result of ggml_nbytes()	commit \| commitdiff \| tree
2023-08-07	Georgi Gerganov	ggml : change params pointer (style change) (#2539)	commit \| commitdiff \| tree
2023-08-07	Georgi Gerganov	ggml : sync (custom ops) (#2537)	commit \| commitdiff \| tree
2023-08-07	Johannes Gäßler	Fixed mmap prefetch for GPU offloading (#2529)	commit \| commitdiff \| tree
2023-08-07	Georgi Gerganov	metal : fix out-of-bounds access + inc concurrency...	commit \| commitdiff \| tree
2023-08-07	GiviMAD	[Makefile] Move ARM CFLAGS before compilation (#2536)	commit \| commitdiff \| tree
2023-08-07	Henri Vasserman	[Zig] Rewrite build for Zig 0.11 (#2514)	commit \| commitdiff \| tree
2023-08-06	DannyDaemonic	console : fix issue related to Windows 11 PowerShell...	commit \| commitdiff \| tree
2023-08-06	Keiichi Tabata	convert.py : add missing abstract methods for quantized...	commit \| commitdiff \| tree
2023-08-05	Johannes Gäßler	CUDA: faster k-quant mul_mat_q kernels (#2525)	commit \| commitdiff \| tree
2023-08-04	Jonas Wunderlich	fix firefox autoscroll (#2519)	commit \| commitdiff \| tree
2023-08-04	Cebtenzzre	server: regenerate completion.js.hpp (#2515)	commit \| commitdiff \| tree
2023-08-04	Cebtenzzre	CUDA: use min compute capability of GPUs actually used...	commit \| commitdiff \| tree
2023-08-04	Cebtenzzre	CUDA: check if event is NULL before cudaStreamWaitEvent...	commit \| commitdiff \| tree
2023-08-04	DannyDaemonic	Add --simple-io option for subprocesses and break out...	commit \| commitdiff \| tree
2023-08-04	Stephen Nichols	Fixing race condition in server and partial stream...	commit \| commitdiff \| tree
2023-08-04	l3utterfly	Stream save llama context data to file instead of alloc...	commit \| commitdiff \| tree
2023-08-04	Borislav Stanimirov	build : fix several cast and printf warnings (#2499)	commit \| commitdiff \| tree
2023-08-03	Evan Jones	examples : generate JSON according to schema (#1887)	commit \| commitdiff \| tree
2023-08-02	Johannes Gäßler	CUDA: faster non k-quant mul_mat_q kernels (#2483)	commit \| commitdiff \| tree
2023-08-02	Johannes Gäßler	CUDA: Fix models with output size != 32000 (#2480)	commit \| commitdiff \| tree
2023-08-02	ldwang	readme : add Aquila-7B model series to supported models...	commit \| commitdiff \| tree
2023-08-02	Eve	tests : Fix compilation warnings (Linux/GCC) (#2451)	commit \| commitdiff \| tree
2023-08-02	Yiming Cui	readme : Add Chinese LLaMA-2 / Alpaca-2 to supported...	commit \| commitdiff \| tree
2023-08-01	Bono Lv	fix a typo in examples/server/README.md (#2478)	commit \| commitdiff \| tree
2023-08-01	ebraminio	server : Support dark mode (#2414)	commit \| commitdiff \| tree
2023-08-01	Matteo Boschini	metal : add gqa8 kernel to allow llama-2-70B on metal...	commit \| commitdiff \| tree
2023-07-31	Johannes Gäßler	CUDA: fixed LLAMA_FAST compilation option (#2473)	commit \| commitdiff \| tree
2023-07-31	Johannes Gäßler	CUDA: fixed cmake F16 option (#2471)	commit \| commitdiff \| tree
2023-07-31	Johannes Gäßler	CUDA: mmq CLI option, fixed mmq build issues (#2453)	commit \| commitdiff \| tree
2023-07-31	Johannes Gäßler	CUDA: Implemented row flattening for non-glm RoPE ...	commit \| commitdiff \| tree
2023-07-31	Johannes Gäßler	CUDA: fewer memory bank conflicts for mul_mat_q (#2458)	commit \| commitdiff \| tree
2023-07-31	slaren	Fix Metal backend broken from the allocator changes...	commit \| commitdiff \| tree
2023-07-30	slaren	ggml : add graph tensor allocator (#2411)	commit \| commitdiff \| tree
2023-07-29	Johannes Gäßler	CUDA: Quantized matrix matrix multiplication (#2160)	commit \| commitdiff \| tree
2023-07-29	Johannes Gäßler	CUDA: faster multi GPU synchronization (#2448)	commit \| commitdiff \| tree
2023-07-28	klosax	perplexity : add Hellaswag calculation (#2389)	commit \| commitdiff \| tree
2023-07-28	Lee	ggml : workaround for missing _mm256_setr_m128i in...	commit \| commitdiff \| tree
2023-07-28	eric8607242	llama : support more diverse tokenizers? (#2420)	commit \| commitdiff \| tree
2023-07-28	Georgi Gerganov	examples : fix whitespace	commit \| commitdiff \| tree
2023-07-28	nhamanasu	examples : server chat mode with llama2 (#2400)	commit \| commitdiff \| tree
2023-07-28	Weird Constructor	readme : fix the description of the Tail free sampling...	commit \| commitdiff \| tree
2023-07-28	Rand Xie	llama : use n_embd_gqa instead of n_embd to handle...	commit \| commitdiff \| tree
2023-07-28	niansa/tuxifan	Obtaining LLaMA 2 instructions (#2308)	commit \| commitdiff \| tree
2023-07-27	mj-shifu	convert.py : Update to support 70B HF format model...	commit \| commitdiff \| tree
2023-07-27	Georgi Gerganov	metal : disable graph concurrency optimization due...	commit \| commitdiff \| tree
2023-07-26	slaren	ggml : fix assert in ggml_set_unary_op (#2410)	commit \| commitdiff \| tree
2023-07-26	Cebtenzzre	make : build with -Wmissing-prototypes (#2394)	commit \| commitdiff \| tree
2023-07-26	slaren	ggml : allocate graphs in a context (#2392)	commit \| commitdiff \| tree
2023-07-25	Kawrakow	Add LLAMA_DEFAULT_RMS_EPS so we can change the default...	commit \| commitdiff \| tree
2023-07-25	slaren	ggml : fix ggml_flash_attn to use op_params (#2387)	commit \| commitdiff \| tree
2023-07-25	ldwang	convert.py : support bpe tokenizer (#2228)	commit \| commitdiff \| tree
2023-07-25	Jiahao Li	ggml : relax contiguous constraints in activation funct...	commit \| commitdiff \| tree
2023-07-25	slaren	ggml : improve graph build time via hash table lookup...	commit \| commitdiff \| tree
2023-07-25	Hesen Peng	build : fix line breaking error in build-info.sh (...	commit \| commitdiff \| tree
2023-07-25	Xiao-Yong Jin	main : add `--in-prefix-bos` to prefix BOS to user...	commit \| commitdiff \| tree
2023-07-25	Eve	ci : add non-AVX scalar build/test (#2356)	commit \| commitdiff \| tree
2023-07-25	katsu560	k_quants : add AVX support to dot functions with QK_K...	commit \| commitdiff \| tree
2023-07-25	Shouzheng Liu	metal : concurrently dispatch commands (#2358)	commit \| commitdiff \| tree
2023-07-25	Kawrakow	Another speed gain for Q4_0 and Q4_1 on Metal (#2375)	commit \| commitdiff \| tree
2023-07-25	Kawrakow	Fix Q4_K and Q5_K for QK_K = 64 on CUDA (#2359)	commit \| commitdiff \| tree
2023-07-25	slaren	server: add rms_norm_eps parameter (#2380)	commit \| commitdiff \| tree
2023-07-25	Henri Vasserman	[Server] Escape HTML in webchat (#2368)	commit \| commitdiff \| tree
2023-07-24	slaren	make rms_norm_eps a parameter (#2374)	commit \| commitdiff \| tree
2023-07-24	Aarni Koskela	Chat UI extras (#2366)	commit \| commitdiff \| tree
2023-07-24	Georgi Gerganov	ggml : sync (unary ops refactor, static-correctness...	commit \| commitdiff \| tree
2023-07-24	Kawrakow	Fix scalar version of Q5_K when QK_K = 64 (#2362)	commit \| commitdiff \| tree
2023-07-24	Evan Jones	llama : add grammar-based sampling (#1773)	commit \| commitdiff \| tree
2023-07-23	Kawrakow	Some more Q4_K and Q5_K speedup on CUDA (#2346)	commit \| commitdiff \| tree
2023-07-23	IgnacioFDM	Add gqa parameter support to the server (#2351)	commit \| commitdiff \| tree
2023-07-23	Johannes Gäßler	Fix __dp4a documentation (#2348)	commit \| commitdiff \| tree
2023-07-23	wzy	common : n_threads == -1 uses std::thread::hardware_con...	commit \| commitdiff \| tree
2023-07-23	slaren	fix n_tasks (#2342)	commit \| commitdiff \| tree
2023-07-23	slaren	ggml: move op parameters from tensors to ggml_tensor...	commit \| commitdiff \| tree
2023-07-23	Georgi Gerganov	llama : grouped-query attention + LLaMAv2 70B support...	commit \| commitdiff \| tree
2023-07-23	maddes8cht	llama : print help to stdout (#2338)	commit \| commitdiff \| tree
2023-07-23	wzy	flake : support `nix build '.#opencl'` (#2337)	commit \| commitdiff \| tree
2023-07-23	Christian Demsar	llama : print max tensor size to stderr (#2336)	commit \| commitdiff \| tree
2023-07-23	Jose Maldonado	make : fix CLBLAST compile support in FreeBSD (#2331)	commit \| commitdiff \| tree
2023-07-23	AustinMroz	examples : simplify vim plugin (#2327)	commit \| commitdiff \| tree
2023-07-23	Jiahao Li	metal : support bcast add & dup & cont op (#2323)	commit \| commitdiff \| tree
2023-07-23	Kawrakow	Speed up Q4_K (#2322)	commit \| commitdiff \| tree
2023-07-22	Johannes Gäßler	CUDA: Fixed 7b q3_K_S with mul_mat_vec_q (#2313)	commit \| commitdiff \| tree
2023-07-22	Georgi Gerganov	llama : optimize memory buffers (#2325)	commit \| commitdiff \| tree
2023-07-22	klosax	Perplexity: Compute scores correlated to HellaSwag...	commit \| commitdiff \| tree
2023-07-22	whoreson	examples : basic VIM plugin	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom