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

2024-12-08	Jeff Bolz	vulkan: compile a test shader in cmake to check for...	commit \| commitdiff \| tree
2024-12-07	Robert Collins	llama : add 128k yarn context for Qwen (#10698)	commit \| commitdiff \| tree
2024-12-07	Xuan Son Nguyen	server : (refactor) no more json in server_task input...	commit \| commitdiff \| tree
2024-12-07	Georgi Gerganov	ggml : disable iq4_nl interleave size 8 (#10709)	commit \| commitdiff \| tree
2024-12-07	Georgi Gerganov	server : various fixes (#10704)	commit \| commitdiff \| tree
2024-12-07	Djip007	ggml : refactor online repacking (#10446)	commit \| commitdiff \| tree
2024-12-07	Georgi Gerganov	server : fix free of spec context and batch (#10651)	commit \| commitdiff \| tree
2024-12-07	0cc4m	Vulkan: VK_KHR_cooperative_matrix support to speed...	commit \| commitdiff \| tree
2024-12-07	Robert Ormandi	metal : Extend how Llama.cpp locates metal resources...	commit \| commitdiff \| tree
2024-12-07	Sukriti Sharma	convert : add support for Roberta embeddings (#10695)	commit \| commitdiff \| tree
2024-12-06	Georgi Gerganov	convert : add custom attention mapping	commit \| commitdiff \| tree
2024-12-06	Xuan Son Nguyen	common : bring back --no-warmup to server (#10686)	commit \| commitdiff \| tree
2024-12-06	Xuan Son Nguyen	server : (refactoring) do not rely on JSON internally...	commit \| commitdiff \| tree
2024-12-05	Plamen Minev	fix(server) : not show alert when DONE is received...	commit \| commitdiff \| tree
2024-12-05	Jeff Bolz	vulkan: Add VK_NV_cooperative_matrix2 support for mul_m...	commit \| commitdiff \| tree
2024-12-05	Riccardo Orlando	llama : add Minerva 7B model support (#10673)	commit \| commitdiff \| tree
2024-12-05	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-12-05	PAB	ggml: add `GGML_SET` Metal kernel + i32 CPU kernel...	commit \| commitdiff \| tree
2024-12-05	PAB	ggml : add `GGML_PAD_REFLECT_1D` operation (ggml/1034)	commit \| commitdiff \| tree
2024-12-05	Daniel Bevenius	py : update outdated copy-paste instructions [no ci...	commit \| commitdiff \| tree
2024-12-04	aryantandon01	Update deprecation-warning.cpp (#10619)	commit \| commitdiff \| tree
2024-12-04	Georgi Gerganov	server : fix speculative decoding with context shift...	commit \| commitdiff \| tree
2024-12-04	Diego Devesa	ggml : add predefined list of CPU backend variants...	commit \| commitdiff \| tree
2024-12-04	Diego Devesa	ggml-cpu : fix HWCAP2_I8MM value (#10646)	commit \| commitdiff \| tree
2024-12-04	ltoniazzi	Fix HF repo commit to clone lora test models (#10649)	commit \| commitdiff \| tree
2024-12-04	JFLFY2255	llama: Support MiniCPM-1B (with & w/o longrope) (#10559)	commit \| commitdiff \| tree
2024-12-04	Jeff Bolz	vulkan: Implement "fast divide" (mul+shift) for unary...	commit \| commitdiff \| tree
2024-12-04	Nicolò Scipione	SYCL : Move to compile time oneMKL interface backend...	commit \| commitdiff \| tree
2024-12-04	Wang Ran (汪然)	fix typo of README.md (#10605)	commit \| commitdiff \| tree
2024-12-04	Frankie Robertson	Avoid using __fp16 on ARM with old nvcc (#10616)	commit \| commitdiff \| tree
2024-12-04	Benson Wong	Add docs for creating a static build (#10268) (#10630)	commit \| commitdiff \| tree
2024-12-04	piDack	clip : add sycl support (#10574)	commit \| commitdiff \| tree
2024-12-03	Jeff Bolz	vulkan: optimize and reenable split_k (#10637)	commit \| commitdiff \| tree
2024-12-03	Xuan Son Nguyen	server : (web ui) Various improvements, now use vite...	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	scripts : remove amx sync	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-12-03	mahorozte	CUDA: remove unnecessary warp reduce in FA (ggml/1032)	commit \| commitdiff \| tree
2024-12-03	PAB	feat: add `GGML_UNARY_OP_ARGMAX` Metal kernel (ggml...	commit \| commitdiff \| tree
2024-12-03	PAB	metal : add `GGML_OP_CONV_TRANSPOSE_1D` kernels (ggml...	commit \| commitdiff \| tree
2024-12-03	Xuan Son Nguyen	llama : add missing LLAMA_API for llama_chat_builtin_te...	commit \| commitdiff \| tree
2024-12-03	Nikolaos Pothitos	readme : add option, update default value, fix formatti...	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	metal : small-batch mat-mul kernels (#10581)	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	github : minify link [no ci] (revert)	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	github : minify link [no ci]	commit \| commitdiff \| tree
2024-12-03	Georgi Gerganov	server : fix default draft model parameters (#10586)	commit \| commitdiff \| tree
2024-12-02	Xuan Son Nguyen	llama : add enum for built-in chat templates (#10623)	commit \| commitdiff \| tree
2024-12-02	Georgi Gerganov	make : deprecate (#10514)	commit \| commitdiff \| tree
2024-12-02	haopeng	server: Add "tokens per second" information in the...	commit \| commitdiff \| tree
2024-12-02	Akarshan Biswas	SYCL: Fix and switch to GGML_LOG system instead of...	commit \| commitdiff \| tree
2024-12-02	Georgi Gerganov	contrib : refresh (#10593)	commit \| commitdiff \| tree
2024-12-01	Juk Armstrong	Add `mistral-v1`, `mistral-v3`, `mistral-v3-tekken...	commit \| commitdiff \| tree
2024-12-01	Georgi Gerganov	grammars : add English-only grammar (#10612)	commit \| commitdiff \| tree
2024-12-01	Wang Qin	ci: add error handling for Python venv creation in...	commit \| commitdiff \| tree
2024-12-01	Diego Devesa	ggml : automatic selection of best CPU backend (#10606)	commit \| commitdiff \| tree
2024-12-01	alek3y	server : bind to any port when specified (#10590)	commit \| commitdiff \| tree
2024-12-01	Georgi Gerganov	readme : update the usage section with examples (#10596)	commit \| commitdiff \| tree
2024-12-01	Wang Qin	build: update Makefile comments for C++ version change...	commit \| commitdiff \| tree
2024-11-30	Adrien Gallouët	ggml-cpu: replace AArch64 NEON assembly with intrinsics...	commit \| commitdiff \| tree
2024-11-30	Georgi Gerganov	readme : remove old badge	commit \| commitdiff \| tree
2024-11-30	Georgi Gerganov	readme : refresh (#10587)	commit \| commitdiff \| tree
2024-11-30	Eve	vulkan: Dynamic subgroup size support for Q6_K mat_vec...	commit \| commitdiff \| tree
2024-11-29	Diego Devesa	ggml : move AMX to the CPU backend (#10570)	commit \| commitdiff \| tree
2024-11-29	Xuan Son Nguyen	server : add more test cases (#10569)	commit \| commitdiff \| tree
2024-11-29	Robert Collins	imatrix : support combine-only (#10492)	commit \| commitdiff \| tree
2024-11-29	Diego Devesa	cleanup UI link list (#10577)	commit \| commitdiff \| tree
2024-11-29	Georgi Gerganov	ggml : fix I8MM Q4_1 scaling factor conversion (#10562)	commit \| commitdiff \| tree
2024-11-29	Shupei Fan	ggml-cpu: fix typo in gemv/gemm iq4_nl_4_4 (#10580)	commit \| commitdiff \| tree
2024-11-29	Alberto Cabrera...	sycl : offload of get_rows set to 0 (#10432)	commit \| commitdiff \| tree
2024-11-29	Alberto Cabrera...	sycl : Reroute permuted mul_mats through oneMKL (#10408)	commit \| commitdiff \| tree
2024-11-29	Chenguang Li	CANN: RoPE operator optimization (#10563)	commit \| commitdiff \| tree
2024-11-29	Jeff Bolz	vulkan: get the first command buffer submitted sooner...	commit \| commitdiff \| tree
2024-11-29	Ting Lou	llava: return false instead of exit (#10546)	commit \| commitdiff \| tree
2024-11-28	Georgi Gerganov	ggml : remove redundant copyright notice + update authors	commit \| commitdiff \| tree
2024-11-28	Georgi Gerganov	llama : add missing model types	commit \| commitdiff \| tree
2024-11-28	Xuan Son Nguyen	server : (tests) don't use thread for capturing stdout...	commit \| commitdiff \| tree
2024-11-28	Johannes Gäßler	common: fix warning message when no GPU found (#10564)	commit \| commitdiff \| tree
2024-11-28	Random Fly	docs: fix outdated usage of llama-simple (#10565)	commit \| commitdiff \| tree
2024-11-28	Diego Devesa	ci : fix tag name in cuda and hip releases (#10566)	commit \| commitdiff \| tree
2024-11-28	Georgi Gerganov	ggml : fix row condition for i8mm kernels (#10561)	commit \| commitdiff \| tree
2024-11-28	Georgi Gerganov	cmake : fix ARM feature detection (#10543)	commit \| commitdiff \| tree
2024-11-28	Shupei Fan	ggml-cpu: support IQ4_NL_4_4 by runtime repack (#10541)	commit \| commitdiff \| tree
2024-11-28	Sergio López	kompute : improve backend to pass test_backend_ops...	commit \| commitdiff \| tree
2024-11-28	Ruixin Huang	CANN: Update cann.md to display correctly in CLion...	commit \| commitdiff \| tree
2024-11-28	leo-pony	CANN: Fix SOC_TYPE compile bug (#10519)	commit \| commitdiff \| tree
2024-11-28	Chenguang Li	CANN: ROPE operator optimization (#10540)	commit \| commitdiff \| tree
2024-11-27	Xuan Son Nguyen	common : fix duplicated file name with hf_repo and...	commit \| commitdiff \| tree
2024-11-27	uvos	Add some minimal optimizations for CDNA (#10498)	commit \| commitdiff \| tree
2024-11-27	Diego Devesa	ci : faster CUDA toolkit installation method and use...	commit \| commitdiff \| tree
2024-11-27	Georgi Gerganov	metal : fix group_norm support condition (#0)	commit \| commitdiff \| tree
2024-11-27	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-11-27	Frankie Robertson	Do not include arm_neon.h when compiling CUDA code...	commit \| commitdiff \| tree
2024-11-27	Jeff Bolz	vulkan: define all quant data structures in types.comp...	commit \| commitdiff \| tree
2024-11-27	Jeff Bolz	vulkan: Handle GPUs with less shared memory (#10468)	commit \| commitdiff \| tree
2024-11-27	Jeff Bolz	vulkan: further optimize q5_k mul_mat_vec (#10479)	commit \| commitdiff \| tree
2024-11-27	Jeff Bolz	vulkan: skip integer div/mod in get_offsets for batch_i...	commit \| commitdiff \| tree
2024-11-27	Jeff Bolz	vulkan: optimize Q2_K and Q3_K mul_mat_vec (#10459)	commit \| commitdiff \| tree
2024-11-26	Diego Devesa	ci : fix cuda releases (#10532)	commit \| commitdiff \| tree
2024-11-26	Shane A	Add OLMo 2 model in docs (#10530)	commit \| commitdiff \| tree
2024-11-26	Diego Devesa	ci : remove nix workflows (#10526)	commit \| commitdiff \| tree
2024-11-26	Diego Devesa	llama : disable warnings for 3rd party sha1 dependency...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom