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

2025-12-25	Aman Gupta	cuda: optimize cumsum cub path (#18362)	commit \| commitdiff \| tree
2025-12-25	Aman Gupta	ggml-cuda: fix blackwell native builds (#18361)	commit \| commitdiff \| tree
2025-12-25	Penglin Cai	CANN: Add support for CONV_TRANSPOSE_1D when kernel...	commit \| commitdiff \| tree
2025-12-25	Aadeshveer...	ggml : optimize cuda cumsum fallback kernel (#18343)	commit \| commitdiff \| tree
2025-12-24	Xuan-Son Nguyen	server: (router) add stop-timeout option (#18350)	commit \| commitdiff \| tree
2025-12-24	Xuan-Son Nguyen	model: support MiMo-V2-Flash (#18328)	commit \| commitdiff \| tree
2025-12-24	Aadeshveer...	fit-params : fix race condition in fit-params output...	commit \| commitdiff \| tree
2025-12-24	Aman Gupta	CUDA: experimental native mxfp4 support for blackwell...	commit \| commitdiff \| tree
2025-12-24	Saba Fallah	model : support for LlamaBidirectionalModel architectur...	commit \| commitdiff \| tree
2025-12-24	Jeff Bolz	vulkan: fix command buffer corruption in ggml_backend_v...	commit \| commitdiff \| tree
2025-12-24	Wang Weixuan	CANN : refactor ACL graph cache (#17752)	commit \| commitdiff \| tree
2025-12-24	Jesse Ikonen	docs: Fix typos in SYCL documentation (#18269)	commit \| commitdiff \| tree
2025-12-24	Ruben Ortlam	vulkan: use fewer FA rows for small cache runs (#18280)	commit \| commitdiff \| tree
2025-12-24	TianHao324	CANN: Uses yarn_ramp cache in ROPE (#17725)	commit \| commitdiff \| tree
2025-12-24	ddh0	common: add `LLAMA_ARG_OVERRIDE_TENSOR` env var for...	commit \| commitdiff \| tree
2025-12-23	Xuan-Son Nguyen	server: return_progress to also report 0% processing...	commit \| commitdiff \| tree
2025-12-23	Pascal	webui: apply webui_settings on first load (#18223)	commit \| commitdiff \| tree
2025-12-23	Xuan-Son Nguyen	server: fix crash with model not having BOS/EOS (#18321)	commit \| commitdiff \| tree
2025-12-23	Daniel Bevenius	model-conversion : add device option to run-org-model...	commit \| commitdiff \| tree
2025-12-23	Chris Rohlf	rpc : add check for rpc buffer type (#18242)	commit \| commitdiff \| tree
2025-12-23	nullname	ggml-hexagon: create generalized functions for cpu...	commit \| commitdiff \| tree
2025-12-23	Daniel Bevenius	model-conversion : add trust_remote_code for embedding...	commit \| commitdiff \| tree
2025-12-23	Neo Zhang	[SYCL] replace llama-cli by llama-completion to rm...	commit \| commitdiff \| tree
2025-12-23	Alessandro98-git	model : fix div-by-zero for Nemotron V2 (#18309)	commit \| commitdiff \| tree
2025-12-22	Ryan Mangeno	model : Granite Embedding support (#15641)	commit \| commitdiff \| tree
2025-12-22	compilade	gguf-py : do not align the data start offset (#18291)	commit \| commitdiff \| tree
2025-12-22	Shouyu	ggml-hexagon: gelu optimization (#18151)	commit \| commitdiff \| tree
2025-12-22	Xuan-Son Nguyen	gen-docs: automatically update markdown file (#18294)	commit \| commitdiff \| tree
2025-12-22	Taimur Ahmad	llamafile: add rvv support for sgemm kernels (#18199)	commit \| commitdiff \| tree
2025-12-22	lhez	opencl: unpack q4_0 for adreno in get_tensor (#18278)	commit \| commitdiff \| tree
2025-12-22	Jeff Bolz	vulkan: Extend rope fusions to allow mrope (#18264)	commit \| commitdiff \| tree
2025-12-22	Xuan-Son Nguyen	server: prevent data race from HTTP threads (#18263)	commit \| commitdiff \| tree
2025-12-22	Xuan-Son Nguyen	server: fix data race in to_json_anthropic (#18283)	commit \| commitdiff \| tree
2025-12-22	Mattt	release: update release workflow to store XCFramework...	commit \| commitdiff \| tree
2025-12-22	Aaron Teo	convert: rework ftype heuristics (#18214)	commit \| commitdiff \| tree
2025-12-22	Xuan-Son Nguyen	server: (docs) remove mention about extra_args (#18262)	commit \| commitdiff \| tree
2025-12-22	Johannes Gäßler	tool/ex/tests: consistently free ctx, then model (...	commit \| commitdiff \| tree
2025-12-21	Jeff Bolz	vulkan: Implement set_tensor_async and the event interf...	commit \| commitdiff \| tree
2025-12-21	Johannes Gäßler	llama: fix RPC for -fit on (#18233)	commit \| commitdiff \| tree
2025-12-21	Xuan-Son Nguyen	move copilot instructions to AGENTS.md (#18259)	commit \| commitdiff \| tree
2025-12-21	Jeff Bolz	vulkan: fix im2col overflowing maxworkgroupcount (...	commit \| commitdiff \| tree
2025-12-21	Jeff Bolz	vulkan/cuda: fix topk_moe with exp_probs_b (#18071)	commit \| commitdiff \| tree
2025-12-21	Jeff Bolz	vulkan: support GGML_UNARY_OP_XIELU (#18062)	commit \| commitdiff \| tree
2025-12-21	Jeff Bolz	vulkan: in graph_optimize, try to group ADD operations...	commit \| commitdiff \| tree
2025-12-21	lovedheart	Vulkan: some improvement on mul_mat_iq2_xs (#18031)	commit \| commitdiff \| tree
2025-12-21	Daniel Bevenius	docs : fix links in parsing.md (#18245)	commit \| commitdiff \| tree
2025-12-21	Aldehir Rojas	common : reorganize includes to prioritize vendored...	commit \| commitdiff \| tree
2025-12-21	Xuan-Son Nguyen	server: add auto-sleep after N seconds of idle (#18228)	commit \| commitdiff \| tree
2025-12-20	Jeff Bolz	tests: Avoid floating point precision false positives...	commit \| commitdiff \| tree
2025-12-20	Jeff Bolz	test-backend-ops: improve msvc build time (#18209)	commit \| commitdiff \| tree
2025-12-20	Aadeshveer...	Added comments explaining thread block size selection...	commit \| commitdiff \| tree
2025-12-20	Oleksandr Kuvshynov	server : [easy] fix per round speculative decode loggin...	commit \| commitdiff \| tree
2025-12-20	Xuan-Son Nguyen	server: support load model on startup, support preset...	commit \| commitdiff \| tree
2025-12-19	Sigbjørn Skjæret	ci : remove non-windows zip artifacts (#18201)	commit \| commitdiff \| tree
2025-12-19	Sigbjørn Skjæret	ci : only save ccache on master (#18207)	commit \| commitdiff \| tree
2025-12-19	Alfred	ggml-hexagon: Implement true Q8_0 quantization on Hexag...	commit \| commitdiff \| tree
2025-12-19	Pascal	arg: fix order to use short form before long form ...	commit \| commitdiff \| tree
2025-12-19	Julius Tischbein	llama : Changing off_t to size_t for Windows (#18204)	commit \| commitdiff \| tree
2025-12-19	Aman Gupta	server: friendlier error msg when ctx < input (#18174)	commit \| commitdiff \| tree
2025-12-19	Xuan-Son Nguyen	presets: refactor, allow cascade presets from different...	commit \| commitdiff \| tree
2025-12-19	Aleksander...	webui: Add editing attachments in user messages (#18147)	commit \| commitdiff \| tree
2025-12-19	Daniel Bevenius	model-conversion : add verbose flag in run-org-model...	commit \| commitdiff \| tree
2025-12-19	Naco Siren	android: fix missing screenshots for Android.md (#18156)	commit \| commitdiff \| tree
2025-12-19	Jeff Bolz	vulkan: Add perf logger mode with concurrency (#17944)	commit \| commitdiff \| tree
2025-12-18	Xuan-Son Nguyen	model : add ASR support for LFM2-Audio-1.5B (conformer...	commit \| commitdiff \| tree
2025-12-18	Pascal	webui: display prompt processing stats (#18146)	commit \| commitdiff \| tree
2025-12-18	Taimur Ahmad	ggml-cpu: extend support for RVV floating-point kernels...	commit \| commitdiff \| tree
2025-12-18	Xuan-Son Nguyen	arg: fix ASAN error on sampler_type_names empty (#18167)	commit \| commitdiff \| tree
2025-12-18	Sigbjørn Skjæret	gguf-py : use copy-on-write mode for localtensor (...	commit \| commitdiff \| tree
2025-12-18	yulo	remove i_major_dual (#18157)	commit \| commitdiff \| tree
2025-12-18	Aleksander...	webui: Fix selecting generated output issues during...	commit \| commitdiff \| tree
2025-12-18	Kim S.	webui: fix chat screen shadow width (#18010)	commit \| commitdiff \| tree
2025-12-18	Johannes Gäßler	llama: offload output layer to GPU first (#18148)	commit \| commitdiff \| tree
2025-12-18	Sigbjørn Skjæret	convert : sort and use file parts from model index...	commit \| commitdiff \| tree
2025-12-18	Julius Tischbein	llama : Async DirectIO model loading on Linux (#18012)	commit \| commitdiff \| tree
2025-12-17	Shouyu	ggml-hexagon: swiglu_oai operation (#18114)	commit \| commitdiff \| tree
2025-12-17	Sigbjørn Skjæret	convert : force patch_merger tensors to f16/f32 (#18124)	commit \| commitdiff \| tree
2025-12-17	Pascal	server: (webui) add --webui-config (#18028)	commit \| commitdiff \| tree
2025-12-17	Xuan-Son Nguyen	server: (router) disable SSL on child process (#18141)	commit \| commitdiff \| tree
2025-12-17	Johannes Gäßler	llama-fit-params: fix memory print (#18136)	commit \| commitdiff \| tree
2025-12-17	Kim S.	webui: fix chat header width when sidebar is closed...	commit \| commitdiff \| tree
2025-12-17	Shouyu	ggml-hexagon: gelu operation (#17921)	commit \| commitdiff \| tree
2025-12-17	Georgi Gerganov	common : restore grammar-based rejection sampling ...	commit \| commitdiff \| tree
2025-12-17	Johannes Gäßler	common: clarify instructions for bug reports (#18134)	commit \| commitdiff \| tree
2025-12-17	HonestQiao	model: fix GLM-ASR-Nano-2512 load error (#18130) (...	commit \| commitdiff \| tree
2025-12-17	Xuan-Son Nguyen	server: (router) allow child process to report status...	commit \| commitdiff \| tree
2025-12-17	Piotr Wilkin...	Extend run-org-model.py, add (a) batching (b) loading...	commit \| commitdiff \| tree
2025-12-17	Johannes Gäßler	Github: ask for -v logs for params_fit [no ci] (#18128)	commit \| commitdiff \| tree
2025-12-17	Alberto Cabrera...	ggml-cpu: ARM64: repack version of q8_0 (dotprod and...	commit \| commitdiff \| tree
2025-12-17	Tarek Dakhran	model: fix LFM2_MOE missing tensors (#18132)	commit \| commitdiff \| tree
2025-12-17	Sigbjørn Skjæret	ci : clean up webui jobs (#18116)	commit \| commitdiff \| tree
2025-12-17	Pascal	common: fix --override-kv to support comma-separated...	commit \| commitdiff \| tree
2025-12-17	yulo	HIP: Refactor mma for RDNA and CDNA (#17990)	commit \| commitdiff \| tree
2025-12-17	Naco Siren	llama.android : Rewrite Android binding (w/o cpu_featur... upstream/0.0.7446	commit \| commitdiff \| tree
2025-12-17	TrevorS	arg: allow -kvu flag for llama-perplexity (#18117)	commit \| commitdiff \| tree
2025-12-17	Aadeshveer...	ggml : use WARP_SIZE/2 for argmax reduction offset...	commit \| commitdiff \| tree
2025-12-17	Yuri Khrustalev	gguf-py : allow converting multi-tensor models from...	commit \| commitdiff \| tree
2025-12-16	Johannes Gäßler	llama-fit-params: force disable mlock (#18103)	commit \| commitdiff \| tree
2025-12-16	Johannes Gäßler	llama-fit-params: lower ctx size for multi GPU (#18101)	commit \| commitdiff \| tree
2025-12-16	Johannes Gäßler	llama-fit-params: fix underflow for dense models (...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom