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

2026-01-06	Tarek Dakhran	mtmd: mtmd_audio_streaming_istft (#18645)	commit \| commitdiff \| tree
2026-01-06	Johannes Gäßler	llama-params-fit: fix last devices with low VRAM (...	commit \| commitdiff \| tree
2026-01-06	Aadeshveer...	ggml : optimize cuda ssm_scan using warp-level reductio...	commit \| commitdiff \| tree
2026-01-06	Xuan-Son Nguyen	arg: use CSV escape style for multiple-value args ...	commit \| commitdiff \| tree
2026-01-06	Jeff Bolz	vulkan: support buffer_from_host_ptr (#18467)	commit \| commitdiff \| tree
2026-01-06	Aman Gupta	ggml-cuda: refactor cuda graph usage (#18637)	commit \| commitdiff \| tree
2026-01-06	Beinsezii	mmq.cu: tune mmq/rocblas switching for RDNA (#18537)	commit \| commitdiff \| tree
2026-01-06	R	server : add thinking content blocks to Anthropic Messa...	commit \| commitdiff \| tree
2026-01-06	Christian Kastner	gguf-py : add requests to dependencies (#18629)	commit \| commitdiff \| tree
2026-01-06	Adrien Gallouët	ggml : fix avx512bf16 build (#18623)	commit \| commitdiff \| tree
2026-01-06	Raul Torres	CANN: Make `valid_values` variable `static const` ...	commit \| commitdiff \| tree
2026-01-05	nwyin	ggml webgpu: add CEIL operation support (#18605)	commit \| commitdiff \| tree
2026-01-05	Tarek Dakhran	model : add LFM2-ColBert-350M (#18607)	commit \| commitdiff \| tree
2026-01-05	Johannes Gäßler	CUDA: fix FA FP16 accumulator overflow for Granite...	commit \| commitdiff \| tree
2026-01-05	tt	add YoutuVLForConditionalGeneration architectures ...	commit \| commitdiff \| tree
2026-01-05	Aman Gupta	ggml-cuda: check for srcs outside the cgraph (#18583)	commit \| commitdiff \| tree
2026-01-05	Vladislav Sayapin	server : fix router child env in containerized environm...	commit \| commitdiff \| tree
2026-01-05	Jeff Bolz	vulkan: fix topk_moe_sigmoid_norm_bias failures in...	commit \| commitdiff \| tree
2026-01-05	Georgi Gerganov	models : fix backend assignment for Granite/Nemotron...	commit \| commitdiff \| tree
2026-01-05	Jeff Bolz	vulkan: handle quantize_q8_1 overflowing the max workgr...	commit \| commitdiff \| tree
2026-01-05	Sigbjørn Skjæret	llama : refactor rope_freq_base/scale_swa conversion...	commit \| commitdiff \| tree
2026-01-05	Chenguang Li	CANN: add operator fusion support for ADD + RMS_NORM...	commit \| commitdiff \| tree
2026-01-05	Francisco Herrera	doc: clarify that steps also apply to linux for opencl...	commit \| commitdiff \| tree
2026-01-05	Ali Tariq	ci : init git lfs in every build for RISC-V (#18590)	commit \| commitdiff \| tree
2026-01-04	Daniel Bevenius	sampling : add support for backend sampling (#17004)	commit \| commitdiff \| tree
2026-01-04	Tarek Dakhran	model : mtmd : make input norm optional in LFM2-VL...	commit \| commitdiff \| tree
2026-01-04	Aman Gupta	CUDA: disable cuda graph when using n-cpu-moe (#18593)	commit \| commitdiff \| tree
2026-01-04	Aman Gupta	ggml-cuda: remove unused params in ggml_cuda_graph...	commit \| commitdiff \| tree
2026-01-03	Aldehir Rojas	common/grammar : replace problematic backtracking regex...	commit \| commitdiff \| tree
2026-01-03	Georgi Gerganov	graph : fix graph reuse logic when `n_pos_per_embd...	commit \| commitdiff \| tree
2026-01-03	Aman Gupta	ggml-cuda: fixes for concurrent streams (#18496)	commit \| commitdiff \| tree
2026-01-03	Georgi Gerganov	context : fix reserve token padding to n_seqs (#18536)	commit \| commitdiff \| tree
2026-01-03	Johannes Gäßler	CUDA: only allocate FA tmp buffer if needed (#18564)	commit \| commitdiff \| tree
2026-01-03	pl752	(Bugfix, ggml-cuda) Pool alloc count fix + small size...	commit \| commitdiff \| tree
2026-01-03	Shouyu	ggml-hexagon: optimize activation function (#18393)	commit \| commitdiff \| tree
2026-01-02	Jeff Bolz	vulkan: Optimize GGML_OP_CUMSUM (#18417)	commit \| commitdiff \| tree
2026-01-02	Jeff Bolz	vulkan: Implement mmvq for iq1_s/iq1_m (#18450)	commit \| commitdiff \| tree
2026-01-02	Prabod	model : Maincoder-1B support (#18534)	commit \| commitdiff \| tree
2026-01-02	Georgi Gerganov	metal : adjust extra size for FA buffer to avoid reallo...	commit \| commitdiff \| tree
2026-01-02	Georgi Gerganov	graph : reduce topology branching (#18548)	commit \| commitdiff \| tree
2026-01-02	Georgi Gerganov	vocab : reduce debug logs about non-EOG control tokens...	commit \| commitdiff \| tree
2026-01-02	Chris Rohlf	rpc : use unordered_map::reserve and emplace (#18513)	commit \| commitdiff \| tree
2026-01-01	MeeMin	cuda : fix copy of large tensors (ggml_nbytes <= INT_MA...	commit \| commitdiff \| tree
2026-01-01	Sigbjørn Skjæret	model : remove modern-bert iswa template (#18529)	commit \| commitdiff \| tree
2026-01-01	tt	model: support youtu-vl model (#18479)	commit \| commitdiff \| tree
2026-01-01	Piotr Wilkin...	Add conversion support for IQuestCoderForCausalLM ...	commit \| commitdiff \| tree
2026-01-01	o7si	model : add support for JinaBertModel with non-gated...	commit \| commitdiff \| tree
2026-01-01	o7si	convert : fix encoding of WPM vocab for BERT models...	commit \| commitdiff \| tree
2026-01-01	HelloKS	model: add Solar Open model (#18511)	commit \| commitdiff \| tree
2026-01-01	Anri Lombard	webui: fix code copy stripping XML/HTML tags (#18518)	commit \| commitdiff \| tree
2026-01-01	Aman Gupta	ggml-cuda: remove unneccesary prints on ggml_cuda_init...	commit \| commitdiff \| tree
2026-01-01	Jeff Bolz	vulkan: extend topk_moe to handle sigmoid w/exp_probs_b...	commit \| commitdiff \| tree
2026-01-01	triplenom	llama: handle short reads in direct I/O path (#18504) upstream/0.0.7599	commit \| commitdiff \| tree
2025-12-31	Anri Lombard	chat: make tool description and parameters optional...	commit \| commitdiff \| tree
2025-12-31	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-12-31	Georgi Gerganov	ggml : bump version to 0.9.5 (ggml/1410)	commit \| commitdiff \| tree
2025-12-31	Anri Lombard	quantize: prevent input/output file collision (#18451)	commit \| commitdiff \| tree
2025-12-31	Sigbjørn Skjæret	convert : lint fix (#18507)	commit \| commitdiff \| tree
2025-12-31	Henry147147	mtmd : Adding support for Nvidia Music Flamingo Model...	commit \| commitdiff \| tree
2025-12-31	gatbontonpc	metal : add count_equal op (#18314)	commit \| commitdiff \| tree
2025-12-31	Johannes Gäßler	CUDA: fix KQ max calculation (#18487)	commit \| commitdiff \| tree
2025-12-31	Georgi Gerganov	metal : remove BF16 x F16 kernels (#18456)	commit \| commitdiff \| tree
2025-12-31	Aman Gupta	sycl: add newline at the end of CMakeLists.txt (#18503)	commit \| commitdiff \| tree
2025-12-31	Rahul Sathe	Work around broken IntelSYCLConfig.cmake in Intel oneAP...	commit \| commitdiff \| tree
2025-12-30	Sigbjørn Skjæret	docker : add CUDA 13.1 image build (#18441)	commit \| commitdiff \| tree
2025-12-30	Bart Louwers	docs : document that JSON Schema is not available to...	commit \| commitdiff \| tree
2025-12-30	Aldehir Rojas	common : default content to an empty string (#18485)	commit \| commitdiff \| tree
2025-12-30	Daniel Bevenius	llama : fix typo in comment in llama-kv-cache.h [no...	commit \| commitdiff \| tree
2025-12-30	Xuan-Son Nguyen	lora: count lora nodes in graph_max_nodes (#18469)	commit \| commitdiff \| tree
2025-12-30	Jay Zenith	sampling: reuse token data buffer in llama_sampler_samp...	commit \| commitdiff \| tree
2025-12-30	Jeff Bolz	server: fix files built redundantly (#18474)	commit \| commitdiff \| tree
2025-12-30	Charles Xu	kleidiai: add and integrate SVE 256-bit vector-length...	commit \| commitdiff \| tree
2025-12-30	Aman Gupta	CUDA: add log line when mxfp4 acceleration is used...	commit \| commitdiff \| tree
2025-12-30	Daniel Bevenius	model-conversion : use CONVERTED_MODEL for compare...	commit \| commitdiff \| tree
2025-12-29	Xuan-Son Nguyen	webui: fix prompt progress ETA calculation (#18468)	commit \| commitdiff \| tree
2025-12-29	Pascal	Webui/prompt processing progress (#18300)	commit \| commitdiff \| tree
2025-12-29	Johannes Gäßler	CUDA: fix replacment of bad archs in CMake (#18457)	commit \| commitdiff \| tree
2025-12-29	wbtek	server : Cmdline arg -to changes http read timeout...	commit \| commitdiff \| tree
2025-12-29	Xuan-Son Nguyen	contributing: tighten AI usage policy (#18388)	commit \| commitdiff \| tree
2025-12-29	Naco Siren	android: routine maintenance - Dec 2025 (#18338)	commit \| commitdiff \| tree
2025-12-29	Georgi Gerganov	server : handle closed connection for tasks (#18459)	commit \| commitdiff \| tree
2025-12-29	Daniel Bevenius	model-conversion : add device option to embd run orig...	commit \| commitdiff \| tree
2025-12-29	Héctor Estrada...	retrieval : use at most n_seq_max chunks (#18400)	commit \| commitdiff \| tree
2025-12-29	o7si	common: fix return value check for setpriority (#18412)	commit \| commitdiff \| tree
2025-12-29	Johannes Gäßler	CUDA: Blackwell features for non-native builds (#18436)	commit \| commitdiff \| tree
2025-12-29	Aman Gupta	cuda: fix race condition in cumsum (#18448)	commit \| commitdiff \| tree
2025-12-28	Tim Neumann	ci : re-enable rocm build on amd64 (#18439)	commit \| commitdiff \| tree
2025-12-28	uvos	HIP: Use mmq on MFMA devices for MUL_MAT_ID in cases...	commit \| commitdiff \| tree
2025-12-28	momonga	model : Plamo3 support (#17304)	commit \| commitdiff \| tree
2025-12-28	Aman Gupta	Revert "ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if...	commit \| commitdiff \| tree
2025-12-28	o7si	rpc: fix segfault on invalid endpoint format (#18387)	commit \| commitdiff \| tree
2025-12-28	Johannes Gäßler	llama-fit-params: fix step size for last device (#18415)	commit \| commitdiff \| tree
2025-12-28	Johannes Gäßler	github: update issue templates [no ci] (#18410)	commit \| commitdiff \| tree
2025-12-28	Xuan-Son Nguyen	mtmd: clarify that we no longer accept AI-generated...	commit \| commitdiff \| tree
2025-12-28	Boian Berberov	cmake: Added more x86_64 CPU backends when building...	commit \| commitdiff \| tree
2025-12-28	QDelta	ggml-cuda: use CMAKE_CUDA_ARCHITECTURES if set when...	commit \| commitdiff \| tree
2025-12-27	lhez	opencl: allow resizing transpose buffers (#18384)	commit \| commitdiff \| tree
2025-12-27	Johannes Gäßler	llama-fit-params: fix overflow check (#18354)	commit \| commitdiff \| tree
2025-12-27	Johannes Gäßler	llama: fix magic number of 999 for GPU layers (#18266)	commit \| commitdiff \| tree
2025-12-27	Aman Gupta	ggml-cuda: Use same regex for GGML_NATIVE=OFF (#18407)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom