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

2024-03-16	AmirAli Mirian	ggml : add AVX512F SIMD (#6088)	commit \| commitdiff \| tree
2024-03-16	Daniel Bevenius	gritlm : add initial README.md (#6086)	commit \| commitdiff \| tree
2024-03-16	Xuan Son Nguyen	readme : add wllama as a wasm binding (#6100)	commit \| commitdiff \| tree
2024-03-16	DAN™	common : refactor nested if causing error C1061 on...	commit \| commitdiff \| tree
2024-03-16	Pierrick Hymbert	ci : close inactive issue with workflow (#6053)	commit \| commitdiff \| tree
2024-03-15	slaren	llama : fix Baichuan2 13B (#6092)	commit \| commitdiff \| tree
2024-03-15	Theia Vogel	llama : add support for control vectors (#5970)	commit \| commitdiff \| tree
2024-03-15	Andrew Canis	llama : add Command-R support (#6033)	commit \| commitdiff \| tree
2024-03-15	Ting Lou	llava : change API to pure C style for Rust FFI bindgen...	commit \| commitdiff \| tree
2024-03-15	slaren	cuda : disable unused cudaLaunchHostFunc code (#6078)	commit \| commitdiff \| tree
2024-03-15	Neo Zhang Jianyu	fix set main gpu error (#6073)	commit \| commitdiff \| tree
2024-03-15	Georgi Gerganov	make : ggml-metal.o depends on ggml.h	commit \| commitdiff \| tree
2024-03-15	AidanBeltonS	[SYCL] Fix non-intel device selection (#6042)	commit \| commitdiff \| tree
2024-03-15	Ondřej Čertík	gguf : add support for I64 and F64 arrays (#6062)	commit \| commitdiff \| tree
2024-03-15	Xuan Son Nguyen	llama : add Orion chat template (#6066)	commit \| commitdiff \| tree
2024-03-15	slaren	llama-bench : use random tokens to improve accuracy...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	llama : fix integer overflow during quantization (...	commit \| commitdiff \| tree
2024-03-14	Steve Grubb	gguf : fix resource leaks (#6061)	commit \| commitdiff \| tree
2024-03-14	Ondřej Čertík	gguf-py : bump version to 0.8.0 (#6060)	commit \| commitdiff \| tree
2024-03-14	Michael Podvitskiy	llama : support models without vocabulary (#5798)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	embedding : add EOS token if not present (#899)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	gguf-py : fix dtype check (#6045)	commit \| commitdiff \| tree
2024-03-14	Jian Liao	readme : improve readme for Llava-1.6 example (#6044)	commit \| commitdiff \| tree
2024-03-14	Pierrick Hymbert	server: disable debug release type sanitizer, simplify...	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	llama : fix typo	commit \| commitdiff \| tree
2024-03-14	Michael Podvitskiy	llama : optimize defrag moves + fix fragmentation calcu...	commit \| commitdiff \| tree
2024-03-14	Ondřej Čertík	gguf-py : add support for I8, I16 and I32 (#6045)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	ggml : designate enum vals for integer types (#6050)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	embedding : print all resulting embeddings (#899)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	metal : build metallib + fix embed path (#6015)	commit \| commitdiff \| tree
2024-03-14	Georgi Gerganov	embedding : print cosine similarity (#899)	commit \| commitdiff \| tree
2024-03-13	Linwei Wang	readme : update details about running llama in Termux...	commit \| commitdiff \| tree
2024-03-13	Georgi Gerganov	readme : update API changes and hot topics	commit \| commitdiff \| tree
2024-03-13	Clint Herron	grammar : handle missing "root" node (#6004)	commit \| commitdiff \| tree
2024-03-13	slaren	llama : add pipeline parallelism support (#6017)	commit \| commitdiff \| tree
2024-03-13	slaren	test-backend-ops : skip CPU backend by default (#6028)	commit \| commitdiff \| tree
2024-03-13	AidanBeltonS	Update get version (#6025)	commit \| commitdiff \| tree
2024-03-13	Xuan Son Nguyen	Server: Use multi-task for embeddings endpoint (#6001)	commit \| commitdiff \| tree
2024-03-12	slaren	ci : remove tidy-review (#6021)	commit \| commitdiff \| tree
2024-03-12	Georgi Gerganov	ggml : reuse quantum structs across backends (#5943)	commit \| commitdiff \| tree
2024-03-12	Georgi Gerganov	ggml : fix UB in IQ2_S and IQ3_S (#6012)	commit \| commitdiff \| tree
2024-03-12	Georgi Gerganov	sycl : update IQ1_S kernels (WIP - not working!) (...	commit \| commitdiff \| tree
2024-03-11	gliptic	grammar : fix unnecessarily retained pointer to rules...	commit \| commitdiff \| tree
2024-03-11	Kawrakow	1.5 bit: we can do even better (#5999)	commit \| commitdiff \| tree
2024-03-11	Georgi Gerganov	llama : more consistent names of count variables (...	commit \| commitdiff \| tree
2024-03-11	Georgi Gerganov	llama : refactor unicode stuff (#5992)	commit \| commitdiff \| tree
2024-03-11	Jakub N	Update server docker image URLs (#5997)	commit \| commitdiff \| tree
2024-03-11	Xuan Son Nguyen	Server: format error to json (#5961)	commit \| commitdiff \| tree
2024-03-11	Michael Podvitskiy	ggml, ci : Windows ARM runner and build fixes (#5979)	commit \| commitdiff \| tree
2024-03-11	Minsoo Cheong	server : maintain chat completion id for streaming...	commit \| commitdiff \| tree
2024-03-11	Gilad S	cmake : fix subdir for `LLAMA_METAL_EMBED_LIBRARY`...	commit \| commitdiff \| tree
2024-03-11	Georgi Gerganov	llama : fix F16/F32 downcast + improve names (#5980)	commit \| commitdiff \| tree
2024-03-11	Kawrakow	Better 1.5 bit quantization (#5971)	commit \| commitdiff \| tree
2024-03-11	Abhilash Majumder	[SYCL] Add q3_s and q1_s (#5886)	commit \| commitdiff \| tree
2024-03-11	AidanBeltonS	[SYCL] Add support for SYCL Nvidia target (#5738)	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	metal : move mm_id indices to shared mem (#5982)	commit \| commitdiff \| tree
2024-03-10	Dean	android : fix utf8 decoding error (#5935)	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	readme : update hot topics	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	ggml : try fix 32-bit arm compat (whisper/1938)	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	ggml : remove __constant__ specifier for CUDA tables...	commit \| commitdiff \| tree
2024-03-10	Pierrick Hymbert	server: ci: windows build and tests (#5968)	commit \| commitdiff \| tree
2024-03-10	DAN™	llama : add support for GritLM (#5959)	commit \| commitdiff \| tree
2024-03-10	Clint Herron	grammar : verify parsed state (#5950)	commit \| commitdiff \| tree
2024-03-10	Georgi Gerganov	nix: update flake.lock (#5969)	commit \| commitdiff \| tree
2024-03-09	Pierrick Hymbert	server: benchmark: chat/completions scenario and other...	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	server : print chat template info	commit \| commitdiff \| tree
2024-03-09	slaren	perplexity : support using multiple sequences to allow...	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	readme : update hot topics	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	ggml : fix unnecessary f32 -> f16 -> f32 casts (mmla...	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	server : fix metrics init (#5964)	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	ggml : remove old quantization functions (#5942)	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	server : clarify some items in the readme (#5957)	commit \| commitdiff \| tree
2024-03-09	SeungWon Jeong	server : normalize embeddings (#5956)	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	tests : gitignore ggml-common.h	commit \| commitdiff \| tree
2024-03-09	Alexey Parfenov	server : fix passing prompt as tokens (#5955)	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	ggml : add ggml-common.h to deduplicate shared code...	commit \| commitdiff \| tree
2024-03-09	Georgi Gerganov	server : simplify logic for empty prompts (#5953)	commit \| commitdiff \| tree
2024-03-09	Xuan Son Nguyen	Server: reorganize some http logic (#5939)	commit \| commitdiff \| tree
2024-03-09	Gabe Goodhart	server : add SSL support (#5926)	commit \| commitdiff \| tree
2024-03-09	Pierrick Hymbert	server: tests: add truncated prompt tests, better kv...	commit \| commitdiff \| tree
2024-03-08	compilade	llama : support Mamba Selective State Space Models...	commit \| commitdiff \| tree
2024-03-08	compilade	llama : fix quantization of shared token_embd (#5944)	commit \| commitdiff \| tree
2024-03-08	Pierrick Hymbert	server: metrics: add llamacpp:prompt_seconds_total...	commit \| commitdiff \| tree
2024-03-08	Don Mahurin	llama : assume tied weights if lm_head/output weights...	commit \| commitdiff \| tree
2024-03-08	Georgi Gerganov	server : fix EOS token detection with disabled cache...	commit \| commitdiff \| tree
2024-03-08	UEXTM.com	log : fix MSVC compile errors (#5643)	commit \| commitdiff \| tree
2024-03-07	Georgi Gerganov	llama-bench : add embeddings option (#5924)	commit \| commitdiff \| tree
2024-03-07	Neo Zhang Jianyu	Revert "[SYCL] fix error when set main gpu to non-zero...	commit \| commitdiff \| tree
2024-03-07	Minsoo Cheong	server : add `/v1/completions` endpoint (#5914)	commit \| commitdiff \| tree
2024-03-07	Georgi Gerganov	server : refactor (#5882)	commit \| commitdiff \| tree
2024-03-07	Neo Zhang Jianyu	[SYCL] fix error when set main gpu to non-zero (#5901)	commit \| commitdiff \| tree
2024-03-06	Jared Van Bortel	ggml : use SYS_get_cpu if SYS_getcpu is not defined...	commit \| commitdiff \| tree
2024-03-06	bobqianic	ggml : use `uint8x16_t` return type for `ggml_vqtbl1q_u...	commit \| commitdiff \| tree
2024-03-06	Georgi Gerganov	convert : remove AWQ remnants (#5768)	commit \| commitdiff \| tree
2024-03-06	Neo Zhang Jianyu	add wait() to make code stable (#5895)	commit \| commitdiff \| tree
2024-03-05	slaren	compare-llama-bench.py : remove mul_mat_q (#5892)	commit \| commitdiff \| tree
2024-03-05	Jared Van Bortel	quants : use MM256_SET_M128I consistently to fix gcc...	commit \| commitdiff \| tree
2024-03-05	ExtReMLapin	grammars : blacklists character control set (#5888)	commit \| commitdiff \| tree
2024-03-05	Georgi Gerganov	Revert "grammars : don't allow to output unescaped...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom