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

2025-11-09	compilade	convert : handle compressed-tensors quant method (...	commit \| commitdiff \| tree
2025-11-09	Georgi Gerganov	server : handle failures to restore host cache (#17078)	commit \| commitdiff \| tree
2025-11-09	Georgi Gerganov	benches : add folder with benchmarks (#16931)	commit \| commitdiff \| tree
2025-11-09	Eric Curtin	Switch to using Ubuntu 25.10 vulkan/mesa (#16497)	commit \| commitdiff \| tree
2025-11-09	Ruben Ortlam	vulkan: iGPU memory reporting fix (#17110)	commit \| commitdiff \| tree
2025-11-09	Ruben Ortlam	vulkan: fix mmq out of bounds reads (#17108)	commit \| commitdiff \| tree
2025-11-09	Jeff Bolz	vulkan: fuse mul_mat_id + mul (#17095)	commit \| commitdiff \| tree
2025-11-09	Georgi Gerganov	metal : retain src and dst buffers during async ops...	commit \| commitdiff \| tree
2025-11-08	Xuan-Son Nguyen	arg: add --cache-list argument to list cached models...	commit \| commitdiff \| tree
2025-11-08	chansikpark	webui: fix keyboard shortcuts for new chat & edit chat...	commit \| commitdiff \| tree
2025-11-08	Jeff Bolz	vulkan: Use spec constants for conv2d s/d/p and kernel...	commit \| commitdiff \| tree
2025-11-08	Aidan	server: fix correct time_ms calculation in prompt_progr...	commit \| commitdiff \| tree
2025-11-08	Aman Gupta	Revert "CUDA: add expert reduce kernel (#16857)" (...	commit \| commitdiff \| tree
2025-11-08	Aman Gupta	CUDA: skip fusion for repeating adds in bias (#17080)	commit \| commitdiff \| tree
2025-11-08	SavicStefan	vulkan: Increase BK to 32; use BK/4 for non-CM mul_mm...	commit \| commitdiff \| tree
2025-11-08	Aleksei Nikiforov	ggml: disable vxe for cross-compilation by default...	commit \| commitdiff \| tree
2025-11-08	Jeff Bolz	vulkan: fuse rms_norm + mul + rope (+ view + set_rows...	commit \| commitdiff \| tree
2025-11-08	Jeff Bolz	vulkan: Fix test-thread-safety crashes (#17024)	commit \| commitdiff \| tree
2025-11-08	Johannes Gäßler	CUDA: fix MMQ stream-k fixup ne1 indices (#17089)	commit \| commitdiff \| tree
2025-11-08	Reese Levine	ggml webgpu: faster matrix multiplication/matrix-vector...	commit \| commitdiff \| tree
2025-11-07	bssrdf	CUDA: properly handle nb00=nb02 case for cpy (#17081)	commit \| commitdiff \| tree
2025-11-07	Acly	vulkan : refactor buffer handling in vk_op_f32 (#16840)	commit \| commitdiff \| tree
2025-11-07	Johannes Gäßler	CUDA: fix should_use_mmvf for ne11 == 1 (#17085)	commit \| commitdiff \| tree
2025-11-07	Georgi Gerganov	bench : cache the llama_context state at computed depth...	commit \| commitdiff \| tree
2025-11-07	Sigbjørn Skjæret	hparams : add n_embd_inp() to support extended embed...	commit \| commitdiff \| tree
2025-11-07	Georgi Gerganov	kv-cache : pad the cache size to 256 for performance...	commit \| commitdiff \| tree
2025-11-07	Adrien Gallouët	Revert "ggml-cpu: detect correct cpu flags for arm64...	commit \| commitdiff \| tree
2025-11-07	iron	ggml-cpu: detect correct cpu flags for arm64 (#16229...	commit \| commitdiff \| tree
2025-11-07	Georgi Gerganov	server : print the samplers chain for each request...	commit \| commitdiff \| tree
2025-11-07	Xuan-Son Nguyen	common: move download functions to download.(cpp\|h...	commit \| commitdiff \| tree
2025-11-06	xctan	ggml-cpu : optimize RVV q2_k and q3_k kernels (#16887)	commit \| commitdiff \| tree
2025-11-06	Johannes Gäßler	CUDA: fix crash on uneven context without FA (#16988)	commit \| commitdiff \| tree
2025-11-06	Georgi Gerganov	metal : initial Metal4 tensor API support (#16634)	commit \| commitdiff \| tree
2025-11-06	Georgi Gerganov	server : disable checkpoints with mtmd (#17045)	commit \| commitdiff \| tree
2025-11-06	Xuan-Son Nguyen	clip: implement minicpm-v sinusoidal embd using GGML...	commit \| commitdiff \| tree
2025-11-06	YehuditE	sycl: add CONCAT operator support (#16047)	commit \| commitdiff \| tree
2025-11-06	Johannes Gäßler	docs: explain CUDA 11 compilation [no ci] (#16824)	commit \| commitdiff \| tree
2025-11-06	l3utterfly	ggml-hexagon: graceful fallback for older socs where...	commit \| commitdiff \| tree
2025-11-05	bssrdf	improve CUDA cpy memory bandwidth when copying transpos...	commit \| commitdiff \| tree
2025-11-05	Jeff Bolz	vulkan: Fix GGML_VULKAN_CHECK_RESULTS to better handle...	commit \| commitdiff \| tree
2025-11-05	Gabe Goodhart	examples(gguf): GGUF example outputs (#17025)	commit \| commitdiff \| tree
2025-11-05	Xuan-Son Nguyen	mtmd: allow QwenVL to process larger image by default...	commit \| commitdiff \| tree
2025-11-05	Georgi Gerganov	server : do not default to multiple slots with speculat...	commit \| commitdiff \| tree
2025-11-05	Xuan-Son Nguyen	mtmd: improve struct initialization (#16981)	commit \| commitdiff \| tree
2025-11-05	손희준	docs: Clarify the endpoint that webui uses (#17001)	commit \| commitdiff \| tree
2025-11-05	Li Pengzhan	model : add openPangu-Embedded (#16941)	commit \| commitdiff \| tree
2025-11-05	Reese Levine	ggml webgpu: minor set rows optimization (#16810)	commit \| commitdiff \| tree
2025-11-05	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-11-05	Georgi Gerganov	ggml : fix conv2d_dw SVE path (ggml/1380)	commit \| commitdiff \| tree
2025-11-05	mnehete32	CUDA: update ops.md (#17005)	commit \| commitdiff \| tree
2025-11-05	lhez	opencl: update doc (#17011)	commit \| commitdiff \| tree
2025-11-04	nullname	refactor: replace sprintf with snprintf for safer strin...	commit \| commitdiff \| tree
2025-11-04	Jeff Bolz	vulkan: remove the need for the dryrun (#16826)	commit \| commitdiff \| tree
2025-11-04	Georgi Gerganov	server : do context shift only while generating (#17000)	commit \| commitdiff \| tree
2025-11-04	Georgi Gerganov	readme : update hot topics (#17002)	commit \| commitdiff \| tree
2025-11-04	Acly	ggml-cpu : bicubic interpolation (#16891)	commit \| commitdiff \| tree
2025-11-04	Sigbjørn Skjæret	ci : apply model label to models (#16994)	commit \| commitdiff \| tree
2025-11-04	Sigbjørn Skjæret	chore : fix models indent after refactor (#16992)	commit \| commitdiff \| tree
2025-11-04	Noah	Fix garbled output with REPACK at high thread counts...	commit \| commitdiff \| tree
2025-11-04	Aman Gupta	CUDA: avoid mul + bias fusion when doing fusion (#16935)	commit \| commitdiff \| tree
2025-11-03	lhez	opencl: support imrope (#16914)	commit \| commitdiff \| tree
2025-11-03	Aleksander...	fix: Viewing multiple PDF attachments (#16974)	commit \| commitdiff \| tree
2025-11-03	Daniel Bevenius	model-conversion : pass config to from_pretrained ...	commit \| commitdiff \| tree
2025-11-03	Georgi Gerganov	server : add props.model_alias (#16943)	commit \| commitdiff \| tree
2025-11-03	theo77186	ggml: CUDA: add head size 72 for flash-attn (#16962)	commit \| commitdiff \| tree
2025-11-03	Xuan-Son Nguyen	mtmd: add --image-min/max-tokens (#16921)	commit \| commitdiff \| tree
2025-11-03	Xuan-Son Nguyen	mtmd: pad mask for qwen2.5vl (#16954)	commit \| commitdiff \| tree
2025-11-03	Jinyang He	ggml : LoongArch fixes (#16958)	commit \| commitdiff \| tree
2025-11-03	Olivier Chafik	sync: minja (glm 4.6 & minmax m2 templates) (#16949)	commit \| commitdiff \| tree
2025-11-03	shani-f	SYCL: optimized repeat_back kernel (3× fewer asm instru...	commit \| commitdiff \| tree
2025-11-02	Sascha Rogmann	feat(webui): improve LaTeX rendering with currency...	commit \| commitdiff \| tree
2025-11-02	Shagun Bera	test-backend-ops : fix segfault in moe-expert-reduce...	commit \| commitdiff \| tree
2025-11-02	Sigbjørn Skjæret	ci : disable failing riscv cross build (#16952)	commit \| commitdiff \| tree
2025-11-02	Zhiyong Wang	model: add Janus Pro for image understanding (#16906)	commit \| commitdiff \| tree
2025-11-02	Georgi Gerganov	clip : use FA (#16837)	commit \| commitdiff \| tree
2025-11-02	Georgi Gerganov	server : support unified cache across slots (#16736)	commit \| commitdiff \| tree
2025-11-02	Aldehir Rojas	common : move gpt-oss reasoning processing to init...	commit \| commitdiff \| tree
2025-11-02	Adrian Lundberg	docs: remove llama_sampler_accept reference in sampling...	commit \| commitdiff \| tree
2025-11-02	mnehete32	CUDA: add FLOOR, CEIL, ROUND, TRUNC unary ops (#16917)	commit \| commitdiff \| tree
2025-11-02	Aaron Teo	devops: fix failing s390x docker build (#16918)	commit \| commitdiff \| tree
2025-11-02	Aaron Teo	ggml: add s390x cpu-feats (#16774)	commit \| commitdiff \| tree
2025-11-01	Georgi Gerganov	scripts : add script to bench models (#16894)	commit \| commitdiff \| tree
2025-11-01	Pascal	webui: auto-refresh /props on inference start to resync...	commit \| commitdiff \| tree
2025-11-01	Pascal	webui: add HTML/JS preview support to MarkdownContent...	commit \| commitdiff \| tree
2025-11-01	Adrien Gallouët	vendor : update cpp-httplib to 0.27.0 (#16846)	commit \| commitdiff \| tree
2025-11-01	Xuan-Son Nguyen	mtmd: refactor preprocessing + support max/min pixels...	commit \| commitdiff \| tree
2025-11-01	Aleksander...	Add a setting to display message generation statistics...	commit \| commitdiff \| tree
2025-11-01	Jaromír Hradílek	webui: recognize AsciiDoc files as valid text files...	commit \| commitdiff \| tree
2025-11-01	Sigbjørn Skjæret	common : allow --system-prompt-file for diffusion-cli...	commit \| commitdiff \| tree
2025-11-01	Sigbjørn Skjæret	codeowners : update after refactor (#16905)	commit \| commitdiff \| tree
2025-11-01	Jeff Bolz	vulkan: Fix multi_add invalid descriptor usage (#16899)	commit \| commitdiff \| tree
2025-11-01	Jeff Bolz	vulkan: fuse mul_mat+add and mul_mat_id+add_id (#16868)	commit \| commitdiff \| tree
2025-11-01	Oliver Simons	CUDA: Remove unneded bias/gate dims in fused mmvq ...	commit \| commitdiff \| tree
2025-10-31	Piotr Wilkin...	refactor : llama-model.cpp (#16252)	commit \| commitdiff \| tree
2025-10-31	Piotr Wilkin...	model : Minimax M2 (#16831)	commit \| commitdiff \| tree
2025-10-31	Giuseppe Scrivano	model : add Granite Hybrid nano types (#16896)	commit \| commitdiff \| tree
2025-10-31	Johannes Gäßler	CUDA: Volta tensor core support for MMF (#16843)	commit \| commitdiff \| tree
2025-10-31	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-10-31	Aman Gupta	CUDA: add expert reduce kernel (#16857)	commit \| commitdiff \| tree
2025-10-31	Georgi Gerganov	batch : fix consistency checks for the input positions...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom