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

2024-10-03	Johannes Gäßler	ggml/ex: calculate accuracy in graph, adapt MNIST ...	commit \| commitdiff \| tree
2024-10-03	Johannes Gäßler	ggml: refactor cross entropy loss CPU impl. (ggml/976)	commit \| commitdiff \| tree
2024-10-03	Jack Mousseau	metal : fix compute pass descriptor autorelease crash...	commit \| commitdiff \| tree
2024-10-03	Diego Devesa	ggml-backend : add device description to CPU backend...	commit \| commitdiff \| tree
2024-10-03	bandoti	ggml: unify backend logging mechanism (#9709)	commit \| commitdiff \| tree
2024-10-03	compilade	convert : handle tokenizer merges format from transform...	commit \| commitdiff \| tree
2024-10-03	Radoslav Gerganov	rpc : enable vulkan (#9714)	commit \| commitdiff \| tree
2024-10-03	Ouadie EL FAROUKI	Fixed dequant precision issues in Q4_1 and Q5_1 (#9711)	commit \| commitdiff \| tree
2024-10-02	Diego Devesa	ggml-backend : add device and backend reg interfaces...	commit \| commitdiff \| tree
2024-10-02	Xuan Son Nguyen	llama : reduce compile time and binary size (#9712)	commit \| commitdiff \| tree
2024-10-02	Alberto Cabrera...	[SYCL] Initial cmake support of SYCL for AMD GPUs ...	commit \| commitdiff \| tree
2024-10-02	Radoslav Gerganov	vulkan : do not use tensor->extra (#9407)	commit \| commitdiff \| tree
2024-10-02	Zhenwei Jin	gguf-split : improve --split and --merge logic (#9619)	commit \| commitdiff \| tree
2024-10-02	Georgi Gerganov	examples : remove benchmark (#9704)	commit \| commitdiff \| tree
2024-10-01	Paweł Wodnicki	Update README.md (#9591)	commit \| commitdiff \| tree
2024-10-01	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-10-01	Johannes Gäßler	test: fix OPT_STEP_ADAMW for test-backend-ops (ggml...	commit \| commitdiff \| tree
2024-10-01	Salvatore Mesoraca	vulkan : mul_mat: fix UB with small warps (ggml/952)	commit \| commitdiff \| tree
2024-10-01	Borislav Stanimirov	ggml : fix ggml_cast (ggml/973)	commit \| commitdiff \| tree
2024-10-01	Johannes Gäßler	ggml: fix gradient allocation logic (ggml/966)	commit \| commitdiff \| tree
2024-10-01	Georgi Gerganov	metal : reduce command encoding overhead (#9698)	commit \| commitdiff \| tree
2024-10-01	Georgi Gerganov	llama : print correct model type for Llama 3.2 1B and 3B	commit \| commitdiff \| tree
2024-10-01	compilade	convert : refactor rope_freqs generation (#9396)	commit \| commitdiff \| tree
2024-09-30	serhii-nakon	Fix Docker ROCM builds, use AMDGPU_TARGETS instead...	commit \| commitdiff \| tree
2024-09-30	compilade	ci : reduce severity of unused Pyright ignore comments...	commit \| commitdiff \| tree
2024-09-30	vb	py : update transfomers version (#9694)	commit \| commitdiff \| tree
2024-09-30	Georgi Gerganov	flake.lock: Update (#9680)	commit \| commitdiff \| tree
2024-09-30	Ruchira Hasaranga	console : utf-8 fix for windows stdin (#9690)	commit \| commitdiff \| tree
2024-09-29	Georgi Gerganov	ggml : define missing HWCAP flags (#9684)	commit \| commitdiff \| tree
2024-09-29	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-09-29	Johannes Gäßler	CUDA: remove bad assert (ggml/972)	commit \| commitdiff \| tree
2024-09-29	Jeff Bolz	vulkan : multithread pipeline creation (ggml/963)	commit \| commitdiff \| tree
2024-09-29	Jeff Bolz	vulkan : fix build for GGML_VULKAN_RUN_TESTS, add TFLOP...	commit \| commitdiff \| tree
2024-09-29	Salvatore Mesoraca	vulkan : argsort barriers must be under uniform control...	commit \| commitdiff \| tree
2024-09-29	Georgi Gerganov	ggml : fix GGML_MAX_N_THREADS + improve formatting...	commit \| commitdiff \| tree
2024-09-29	matiaslin	common : ensure llama_batch size does not exceed max...	commit \| commitdiff \| tree
2024-09-29	nopperl	py : add model class for Chameleon conversion (#9683)	commit \| commitdiff \| tree
2024-09-29	Georgi Gerganov	contrib : add Resources section (#9675)	commit \| commitdiff \| tree
2024-09-28	Georgi Gerganov	llama : add reranking support (#9510)	commit \| commitdiff \| tree
2024-09-28	slaren	test-backend-ops : use flops for some performance tests...	commit \| commitdiff \| tree
2024-09-28	Georgi Gerganov	llama : add comment about thread-safety [no ci] (#9449)	commit \| commitdiff \| tree
2024-09-28	Zhenwei Jin	vocab : refactor tokenizer to reduce init overhead...	commit \| commitdiff \| tree
2024-09-28	nopperl	llama : add support for Chameleon (#8543)	commit \| commitdiff \| tree
2024-09-28	Aarni Koskela	readme : add tool (#9655)	commit \| commitdiff \| tree
2024-09-28	Dan Johansson	ggml : add run-time detection of neon, i8mm and sve...	commit \| commitdiff \| tree
2024-09-28	Markus Tavenrath	Enable use to the rebar feature to upload buffers to...	commit \| commitdiff \| tree
2024-09-27	Georgi Gerganov	readme : update hot topics	commit \| commitdiff \| tree
2024-09-27	Borislav Stanimirov	cmake : add option for common library (#9661)	commit \| commitdiff \| tree
2024-09-26	Neo Zhang Jianyu	[SYCL] add missed dll file in package (#9577)	commit \| commitdiff \| tree
2024-09-26	R0CKSTAR	mtgpu: enable VMM (#9597)	commit \| commitdiff \| tree
2024-09-25	Xuan Son Nguyen	ci : fix docker build number and tag name (#9638)	commit \| commitdiff \| tree
2024-09-25	Charles Xu	ggml : remove assert for AArch64 GEMV and GEMM Q4 kerne...	commit \| commitdiff \| tree
2024-09-25	Xuan Son Nguyen	server : add more env vars, improve gen-docs (#9635)	commit \| commitdiff \| tree
2024-09-25	Gabe Goodhart	llama : add IBM Granite MoE architecture (#9438)	commit \| commitdiff \| tree
2024-09-25	Dou Xinpeng	cann: fix crash when llama-bench is running on multiple...	commit \| commitdiff \| tree
2024-09-24	Eric Zhang	ggml : add AVX512DQ requirement for AVX512 builds ...	commit \| commitdiff \| tree
2024-09-24	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-09-24	Georgi Gerganov	examples : adapt to ggml.h changes (ggml/0)	commit \| commitdiff \| tree
2024-09-24	Georgi Gerganov	llama : keep track of all EOG tokens in the vocab ...	commit \| commitdiff \| tree
2024-09-24	Georgi Gerganov	log : add CONT level for continuing previous log entry...	commit \| commitdiff \| tree
2024-09-24	StrangeBytesDev	server : add newline after chat example (#9616)	commit \| commitdiff \| tree
2024-09-24	Georgi Gerganov	sampling : avoid expensive softmax during greedy sampli...	commit \| commitdiff \| tree
2024-09-24	Max Krasnyansky	threads: fix msvc build without openmp (#9615)	commit \| commitdiff \| tree
2024-09-24	Ivan	cuda: add q8_0->f32 cpy operation (#9571)	commit \| commitdiff \| tree
2024-09-23	Xuan Son Nguyen	server : add --no-context-shift option (#9607)	commit \| commitdiff \| tree
2024-09-23	Max Krasnyansky	threads: improve ggml_barrier scaling with large number...	commit \| commitdiff \| tree
2024-09-23	Riceball LEE	readme : add programmable prompt engine language CLI...	commit \| commitdiff \| tree
2024-09-23	Georgi Gerganov	flake.lock: Update (#9586)	commit \| commitdiff \| tree
2024-09-23	Srihari-mcw	ggml : AVX512 gemm for Q4_0_8_8 (#9532)	commit \| commitdiff \| tree
2024-09-23	Georgi Gerganov	perplexity : remove extra new lines after chunks (...	commit \| commitdiff \| tree
2024-09-23	Georgi Gerganov	metal : use F32 prec for K*Q in vec FA (#9595)	commit \| commitdiff \| tree
2024-09-23	Akarshan Biswas	Revert "[SYCL] fallback mmvq (#9088)" (#9579)	commit \| commitdiff \| tree
2024-09-22	R0CKSTAR	musa: enable building fat binaries, enable unified...	commit \| commitdiff \| tree
2024-09-22	Molly Sophia	Fix merge error in #9454 (#9589)	commit \| commitdiff \| tree
2024-09-22	Johannes Gäßler	CUDA: enable Gemma FA for HIP/Pascal (#9581)	commit \| commitdiff \| tree
2024-09-22	Shankar	llama: remove redundant loop when constructing ubatch...	commit \| commitdiff \| tree
2024-09-22	Molly Sophia	RWKV v6: RWKV_WKV op CUDA implementation (#9454)	commit \| commitdiff \| tree
2024-09-21	slaren	ggml-alloc : fix list of allocated tensors with GGML_AL...	commit \| commitdiff \| tree
2024-09-21	agray3	Update CUDA graph on scale change plus clear nodes...	commit \| commitdiff \| tree
2024-09-21	Huang Qi	CI: Provide prebuilt windows binary for hip (#9467)	commit \| commitdiff \| tree
2024-09-20	slaren	quantize : improve type name parsing (#9570)	commit \| commitdiff \| tree
2024-09-20	Georgi Gerganov	ggml : fix builds (#0)	commit \| commitdiff \| tree
2024-09-20	Georgi Gerganov	ggml : fix trailing whitespace (#0)	commit \| commitdiff \| tree
2024-09-20	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2024-09-20	Johannes Gäßler	ggml/examples: add backend support for numerical optimi...	commit \| commitdiff \| tree
2024-09-20	Georgi Gerganov	examples : add null threadpool args where needed (ggml/0)	commit \| commitdiff \| tree
2024-09-20	Johannes Gäßler	CUDA: fix sum.cu compilation for CUDA < 11.7 (#9562)	commit \| commitdiff \| tree
2024-09-20	Georgi Gerganov	examples : flush log upon ctrl+c (#9559)	commit \| commitdiff \| tree
2024-09-20	Sigbjørn Skjæret	perplexity : do not escape input data by default (...	commit \| commitdiff \| tree
2024-09-19	Georgi Gerganov	server : clean-up completed tasks from waiting list...	commit \| commitdiff \| tree
2024-09-19	Sigbjørn Skjæret	imatrix : disable prompt escape by default (#9543)	commit \| commitdiff \| tree
2024-09-18	slaren	ggml : fix n_threads_cur initialization with one thread...	commit \| commitdiff \| tree
2024-09-18	Georgi Gerganov	scripts : verify py deps at the start of compare (...	commit \| commitdiff \| tree
2024-09-18	Daniel Bevenius	llama : use reserve/emplace_back in sampler_sample...	commit \| commitdiff \| tree
2024-09-18	Vinesh Janarthanan	server : match OAI structured output response (#9527)	commit \| commitdiff \| tree
2024-09-18	Eric Zhang	server : fix OpenSSL build (remove obsolete `LOG_INFO...	commit \| commitdiff \| tree
2024-09-18	Neo Zhang Jianyu	[SYCL]set context default value to avoid memory issue...	commit \| commitdiff \| tree
2024-09-17	Michael Podvitskiy	llama-bench: correct argument parsing error message...	commit \| commitdiff \| tree
2024-09-17	Bert Wagner	arg : add env variable for parallel (#9513)	commit \| commitdiff \| tree
2024-09-17	Michael Podvitskiy	llama : fix n_vocab init for 'no_vocab' case (#9511)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom