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

2025-03-26	Georgi Gerganov	ggml : fix MUL_MAT_ID repack with Q8_K (#12544)	commit \| commitdiff \| tree
2025-03-26	R0CKSTAR	doc: [MUSA] minor changes (#12583)	commit \| commitdiff \| tree
2025-03-25	Sigbjørn Skjæret	convert: fix Mistral3/Gemma3 model hparams init (#12571)	commit \| commitdiff \| tree
2025-03-25	Eric Curtin	run: de-duplicate fmt and format functions and optimize...	commit \| commitdiff \| tree
2025-03-25	Dan Johansson	ggml-cpu : update KleidiAI to v1.5.0 (#12568)	commit \| commitdiff \| tree
2025-03-25	Akarshan Biswas	SYCL: disable Q4_0 reorder optimization (#12560)	commit \| commitdiff \| tree
2025-03-25	Dan Johansson	docs : add build instructions for KleidiAI (#12563)	commit \| commitdiff \| tree
2025-03-25	R0CKSTAR	ci: [MUSA] add CI and update doc (#12562)	commit \| commitdiff \| tree
2025-03-25	Georgi Gerganov	context : fix worst-case reserve outputs (#12545)	commit \| commitdiff \| tree
2025-03-24	Akarshan Biswas	ci: [SYCL] ggml-ci Use main GPU and enable sysman ...	commit \| commitdiff \| tree
2025-03-24	lhez	opencl: simplify kernel embedding logic in cmakefile...	commit \| commitdiff \| tree
2025-03-24	Akarshan Biswas	CI: fix SYCL build (#12546)	commit \| commitdiff \| tree
2025-03-24	Tei Home	docs: update: improve the Fedoa CUDA guide (#12536)	commit \| commitdiff \| tree
2025-03-24	compilade	llama-vocab : add SuperBPE pre-tokenizer (#12532)	commit \| commitdiff \| tree
2025-03-24	R0CKSTAR	CUDA: Fix clang warnings (#12540)	commit \| commitdiff \| tree
2025-03-24	Prajwal B Mehendarkar	mmap : skip resource limit checks on AIX (#12541)	commit \| commitdiff \| tree
2025-03-24	Jeff Bolz	vulkan: fix mul_mat_vec failure in backend tests (...	commit \| commitdiff \| tree
2025-03-23	Marius Gerdes	server : Add verbose output to OAI compatible chat...	commit \| commitdiff \| tree
2025-03-23	Lars Sonchocky...	install : add macports (#12518)	commit \| commitdiff \| tree
2025-03-22	Xuan-Son Nguyen	llama : gemma3 : use output tensor if it exists in...	commit \| commitdiff \| tree
2025-03-22	Georgi Gerganov	ggml : fix quantized cpy op (#12310)	commit \| commitdiff \| tree
2025-03-22	R0CKSTAR	musa: refine compute capability (#12493)	commit \| commitdiff \| tree
2025-03-22	Jeff Bolz	vulkan: Optimize mul_mat_vec p021 and nc shaders (...	commit \| commitdiff \| tree
2025-03-21	stduhpf	Vulkan: RTE rounding for cpy to quant (#12480)	commit \| commitdiff \| tree
2025-03-21	Eve	vulkan: workaround for AMD Windows driver 16 bit unpack...	commit \| commitdiff \| tree
2025-03-21	Georgi Gerganov	model : do not repack if a GPU device is present (...	commit \| commitdiff \| tree
2025-03-21	Sigbjørn Skjæret	chore : cleanup llama_model_loader::TENSOR_ usage ...	commit \| commitdiff \| tree
2025-03-21	marcoStocchi	llama-tts : avoid crashes related to bad model file...	commit \| commitdiff \| tree
2025-03-21	蕭澧邦	[SYCL] Fix build on Windows when ccache enabled (#9954...	commit \| commitdiff \| tree
2025-03-21	Svetlozar Georgiev	sycl: cleanup oneDNN related code (#12097)	commit \| commitdiff \| tree
2025-03-20	Woof Dog	webui : Prevent rerendering on textarea input (#12299)	commit \| commitdiff \| tree
2025-03-20	Sigbjørn Skjæret	llama : make Qwen2MoE QKV bias optional (#12477)	commit \| commitdiff \| tree
2025-03-20	Srihari-mcw	ggml : block interleaving support for Q4_K quantization...	commit \| commitdiff \| tree
2025-03-20	Bartowski	convert : avoid calls to tokenizer.added_tokens_decoder...	commit \| commitdiff \| tree
2025-03-19	fairydreaming	context : clear sets containing encoder output sequence...	commit \| commitdiff \| tree
2025-03-19	Gaurav Garg	CUDA: Improve flash decoding kernel GPU occupancy for...	commit \| commitdiff \| tree
2025-03-19	Jeff Bolz	vulkan: optimize iq1 coopmat2 dequant functions (#12427)	commit \| commitdiff \| tree
2025-03-19	Guus Waals	Fix visionOS build and add CI (#12415)	commit \| commitdiff \| tree
2025-03-19	Sigbjørn Skjæret	llama : add support for GPT2, Bloom and CodeShell tied...	commit \| commitdiff \| tree
2025-03-19	Sigbjørn Skjæret	convert : Support chat_template.json (#12460)	commit \| commitdiff \| tree
2025-03-19	Jeff Bolz	vulkan: Submit once enough matmul work has been recorde...	commit \| commitdiff \| tree
2025-03-18	lhez	opencl: improve profiling (#12442)	commit \| commitdiff \| tree
2025-03-18	Georgi Gerganov	graph : normalize Q, K, V shapes + sync cross attention...	commit \| commitdiff \| tree
2025-03-18	R0CKSTAR	musa: override warp_size of musa device to 32 (#12445)	commit \| commitdiff \| tree
2025-03-18	Xuan-Son Nguyen	llama : support converting Mistral Small text-only...	commit \| commitdiff \| tree
2025-03-18	Georgi Gerganov	speculative : fix seg fault in certain cases (#12454)	commit \| commitdiff \| tree
2025-03-18	Xuan-Son Nguyen	llama : add support for EXAONE tied word embeddings...	commit \| commitdiff \| tree
2025-03-18	Georgi Gerganov	context : always use non-causal attention for encoder...	commit \| commitdiff \| tree
2025-03-18	Łukasz Ślusarczyk	SYCL: using graphs is configurable by environment varia...	commit \| commitdiff \| tree
2025-03-18	Georgi Gerganov	server : fix warmup draft cache type (#12446)	commit \| commitdiff \| tree
2025-03-18	Prajwal B Mehendarkar	cmake : fix PowerPC build (#12241)	commit \| commitdiff \| tree
2025-03-18	fj-y-saito	ggml : add SVE support for q6_K_q8_K (#12361)	commit \| commitdiff \| tree
2025-03-18	0cc4m	Vulkan: Default to 1GB allocations instead of 4GB to...	commit \| commitdiff \| tree
2025-03-18	Łukasz Ślusarczyk	fixed compilation warnings in ggml-sycl (#12424)	commit \| commitdiff \| tree
2025-03-17	Molly Sophia	llama: Add support for RWKV v7 architecture (#12412)	commit \| commitdiff \| tree
2025-03-17	Sigbjørn Skjæret	docs : bring llama-cli conversation/template docs up...	commit \| commitdiff \| tree
2025-03-17	Gaurav Garg	cuda : enable CUDA Graph on CUDA Toolkit < 12.x (#12394)	commit \| commitdiff \| tree
2025-03-17	Guus Waals	ggml-vulkan: remove unused find_program(glslc) (#12416)	commit \| commitdiff \| tree
2025-03-17	Jeff Bolz	vulkan: Add N/2 and N/4 optimized paths in coopmat2...	commit \| commitdiff \| tree
2025-03-17	Daniele	vulkan: subgroup size tuning (#12087)	commit \| commitdiff \| tree
2025-03-17	Jeff Bolz	vulkan: use fp32 in coopmat2 q4_k dequant function...	commit \| commitdiff \| tree
2025-03-17	Jeff Bolz	vulkan: Pad N dimension of B matrix for coopmat2 perf...	commit \| commitdiff \| tree
2025-03-17	Jeff Bolz	vulkan: Adjust coopmat2 tile sizes and selection heuris...	commit \| commitdiff \| tree
2025-03-17	Christian Kastner	cmake : enable building llama.cpp using system libggml...	commit \| commitdiff \| tree
2025-03-17	Akarshan Biswas	SYCL: set extras only on GGML_TYPE_Q4_0 (#12366)	commit \| commitdiff \| tree
2025-03-16	Sigbjørn Skjæret	llama : fix OLMo-2-0325-32B-Instruct K-norm size (...	commit \| commitdiff \| tree
2025-03-16	Georgi Gerganov	context : fix init of n_outputs (#12397)	commit \| commitdiff \| tree
2025-03-16	Daniel Bevenius	ci : add --symlinks to xcframework zip command (#12409)	commit \| commitdiff \| tree
2025-03-15	marcoStocchi	llama-tts : add '-o' option (#12398)	commit \| commitdiff \| tree
2025-03-15	aubreyli	SYCL: Delete redundant plus sign and space (#12391)	commit \| commitdiff \| tree
2025-03-15	fairydreaming	SYCL : support non-contiguous tensors in binary ops...	commit \| commitdiff \| tree
2025-03-15	Chenguang Li	[CANN]MUL_MAT optimization (#12382)	commit \| commitdiff \| tree
2025-03-14	Eric Curtin	Add CLI arg to llama-run to adjust the number of thread...	commit \| commitdiff \| tree
2025-03-14	Sigbjørn Skjæret	main : add -sysf / --system-prompt-file (#12249) (...	commit \| commitdiff \| tree
2025-03-14	fairydreaming	Load all MoE experts during warmup (#11571)	commit \| commitdiff \| tree
2025-03-14	Victor	server: fix "--grammar-file" parameter (#12285)	commit \| commitdiff \| tree
2025-03-14	Georgi Gerganov	graph : simplify attn input build for unified KV cache...	commit \| commitdiff \| tree
2025-03-14	Georgi Gerganov	hparams : add SWA rope parameters (#12374)	commit \| commitdiff \| tree
2025-03-13	Georgi Gerganov	llama : fix Gemma3 SWA KV cache shift (#12373)	commit \| commitdiff \| tree
2025-03-13	Xuan-Son Nguyen	arg : no n_predict = -2 for examples except for main...	commit \| commitdiff \| tree
2025-03-13	Georgi Gerganov	llama : refactor llama_context, llama_kv_cache, llm_bui...	commit \| commitdiff \| tree
2025-03-13	Ishaan Gandhi	server : fix crash when using verbose output with input...	commit \| commitdiff \| tree
2025-03-12	Oscar Barenys	Update build.yml for Windows Vulkan builder to use...	commit \| commitdiff \| tree
2025-03-12	Daniel Bevenius	llama.swiftui : fix xcframework dir in README [no ci...	commit \| commitdiff \| tree
2025-03-12	Alberto Cabrera...	sycl : variable sg_size support for mmvq kernels (...	commit \| commitdiff \| tree
2025-03-12	uvos	CUDA/HIP: Fix fattn-vec-* when device warp size is...	commit \| commitdiff \| tree
2025-03-12	Xuan-Son Nguyen	llama : Add Gemma 3 support (+ experimental vision...	commit \| commitdiff \| tree
2025-03-12	Jeff Bolz	vulkan: fix bug in coopmat1 mul_mat_id (#12316)	commit \| commitdiff \| tree
2025-03-11	uvos	CUDA/HIP: refractor mmqv to unify the calculation of...	commit \| commitdiff \| tree
2025-03-11	jklincn	ggml-backend : fix backend search path (#12330)	commit \| commitdiff \| tree
2025-03-11	BB-fat	metal : Cache the Metal library at the device context...	commit \| commitdiff \| tree
2025-03-11	Xuan-Son Nguyen	clip : bring back GPU support (#12322)	commit \| commitdiff \| tree
2025-03-10	Eve	mat vec double buffer (#12188)	commit \| commitdiff \| tree
2025-03-10	R0CKSTAR	musa: support new arch mp_31 and update doc (#12296)	commit \| commitdiff \| tree
2025-03-10	Henry Linjamäki	opencl: use OpenCL C standard supported by the device...	commit \| commitdiff \| tree
2025-03-10	John Bean	readme: added Sidekick to available UIs (#12311)	commit \| commitdiff \| tree
2025-03-10	Georgi Gerganov	tests : fix test-quantize-fns to init the CPU backend...	commit \| commitdiff \| tree
2025-03-10	marcoStocchi	common : refactor '-o' option (#12278)	commit \| commitdiff \| tree
2025-03-10	Olivier Chafik	`server`: extract <think> tags from qwq outputs (#12297)	commit \| commitdiff \| tree
2025-03-10	Olivier Chafik	`tool-call`: ensure there's always a non-empty tool...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom