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

2026-04-23	Tarek Dakhran	server: Enable transcriptions API for LFM2-Audio (...	commit \| commitdiff \| tree
2026-04-23	Georgi Gerganov	metal : fix event synchronization (#22260)	commit \| commitdiff \| tree
2026-04-23	Georgi Gerganov	gitignore: add AGENTS.local.md (#22246)	commit \| commitdiff \| tree
2026-04-23	Georgi Gerganov	ggml-base: use MATH_LIBRARY variable instead of hardcod...	commit \| commitdiff \| tree
2026-04-23	Neo Zhang Jianyu	[SYCL] Update oneapi 2025.3.3, Seperate SYCL build...	commit \| commitdiff \| tree
2026-04-23	ynankani	convert : Handle ModelOpt produced mixed precision...	commit \| commitdiff \| tree
2026-04-23	abotsis	sycl : fused MoE mul_mat_vec_q for TG (#21920)	commit \| commitdiff \| tree
2026-04-23	Chen Yuan	ggml-webgpu: add support for im2col (#22259)	commit \| commitdiff \| tree
2026-04-23	Anav Prasad	CUDA: fuse relu + sqr (#22249)	commit \| commitdiff \| tree
2026-04-23	uvos	HIP: flip GGML_HIP_GRAPHS to default on (#22254)	commit \| commitdiff \| tree
2026-04-22	Nikhil Jain	[WebGPU] Implement async tensor api and event api ...	commit \| commitdiff \| tree
2026-04-22	Masashi Yoshimura	ggml-webgpu: Add fused RMS_NORM + MUL (#21983)	commit \| commitdiff \| tree
2026-04-22	Piotr Wilkin...	chat: fix parallel_tool_calls default setting based...	commit \| commitdiff \| tree
2026-04-22	Georgi Gerganov	speculative-simple : add checkpoint support (#22227)	commit \| commitdiff \| tree
2026-04-22	Akarshan Biswas	sycl: Improve mul_mat_id memory efficiency and add...	commit \| commitdiff \| tree
2026-04-22	Xuan-Son Nguyen	mtmd: also support LLAMA_ROPE_TYPE_NONE (#22242)	commit \| commitdiff \| tree
2026-04-22	Xuan-Son Nguyen	server: ignore reasoning content from transcription...	commit \| commitdiff \| tree
2026-04-22	manayang	mtmd, llama : Update HunyuanVL vision-language model...	commit \| commitdiff \| tree
2026-04-22	Ethan Turner	common: Refactoring sampler parameters (#20429) (#22233)	commit \| commitdiff \| tree
2026-04-22	Piotr Wilkin...	common/chat, server: refactor, move all conversion...	commit \| commitdiff \| tree
2026-04-22	Chen Yuan	ggml-webgpu(shader): support conv2d kernels. (#21964)	commit \| commitdiff \| tree
2026-04-21	Aparna M P	hexagon: add support for FILL op (#22198)	commit \| commitdiff \| tree
2026-04-21	Masashi Yoshimura	ggml-webgpu: reset CPU/GPU profiling time when freeing...	commit \| commitdiff \| tree
2026-04-21	Xuan-Son Nguyen	server: allow cancel loading model (#21814)	commit \| commitdiff \| tree
2026-04-21	Shreya Jain	Hexagon: DAIG op (#22195)	commit \| commitdiff \| tree
2026-04-21	Mengsheng Wu	hexagon: fix missing v79 entry in libggml-htp.inf ...	commit \| commitdiff \| tree
2026-04-21	Paul Dubs	spec : reset i_last when low acceptance streak occurs...	commit \| commitdiff \| tree
2026-04-21	Kwa Jie Hao	mtmd: Add support for Reka Edge 2603 (#21616)	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	arg : add --spec-default (#22223)	commit \| commitdiff \| tree
2026-04-21	Zijun Yu	openvino: driver setup, CI split, thread safety, and...	commit \| commitdiff \| tree
2026-04-21	Alessandro...	vendor : update cpp-httplib to 0.43.1 (#22143)	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	metal : workaround macOS GPU interactivity watchdog...	commit \| commitdiff \| tree
2026-04-21	Jeff Bolz	vulkan: Support F16 OP_FILL (#22177)	commit \| commitdiff \| tree
2026-04-21	Xuan-Son Nguyen	mtmd: correct mtmd_decode_use_mrope() (#22188)	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	llama-ext : fix exports (#22202)	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	ggml : bump version to 0.10.0 (ggml/1463)	commit \| commitdiff \| tree
2026-04-21	Georgi Gerganov	fit-params : refactor + add option to output estimated...	commit \| commitdiff \| tree
2026-04-21	xris99	server : fix hardcoded proxy connection timeout in...	commit \| commitdiff \| tree
2026-04-20	leonardHONG	ggml-cuda: flush legacy pool on OOM and retry (#22155)	commit \| commitdiff \| tree
2026-04-20	Xuan-Son Nguyen	mtmd: correct get_n_pos / get_decoder_pos (#22175)	commit \| commitdiff \| tree
2026-04-20	Georgi Gerganov	server : remove /api endpoints (#22165)	commit \| commitdiff \| tree
2026-04-20	Gaurav Garg	Tensor-parallel: Fix delayed AllReduce on Gemma-4 MoE...	commit \| commitdiff \| tree
2026-04-20	Johannes Gäßler	TP: fix 0-sized tensor slices, AllReduce fallback ...	commit \| commitdiff \| tree
2026-04-20	pl752	ggml-cpu: Optimized x86 and generic cpu q1_0 dot (follo...	commit \| commitdiff \| tree
2026-04-20	neha-ha	ggml-webgpu: updated matrix-vector multiplication ...	commit \| commitdiff \| tree
2026-04-20	Xuan-Son Nguyen	mtmd: refactor mtmd_decode_use_mrope (#22161)	commit \| commitdiff \| tree
2026-04-20	SamareshSingh	fix: GLM-DSA crash in llama-tokenize when using vocab_o...	commit \| commitdiff \| tree
2026-04-20	Georgi Gerganov	server : refactor "use checkpoint" logic (#22114)	commit \| commitdiff \| tree
2026-04-20	Katostrofik	[SYCL] Fix reorder MMVQ assert on unaligned vocab sizes...	commit \| commitdiff \| tree
2026-04-20	Yes You Can...	server: rename --clear-idle to --cache-idle-slots ...	commit \| commitdiff \| tree
2026-04-19	Alessandro...	vendor : update cpp-httplib to 0.42.0 (#21781)	commit \| commitdiff \| tree
2026-04-19	Johannes Gäßler	CUDA: refactor mma data loading for AMD (#22051)	commit \| commitdiff \| tree
2026-04-19	Aldehir Rojas	common/autoparser : allow space after tool call (#22073)	commit \| commitdiff \| tree
2026-04-19	uvos	HIP: Remove unesscary NCCL_CHECK (#21914)	commit \| commitdiff \| tree
2026-04-19	Xuan-Son Nguyen	mtmd: add pos_0 to mtmd_image_tokens_get_decoder_pos...	commit \| commitdiff \| tree
2026-04-19	Gaurav Garg	ggml : reduce CPU overhead in meta backend (#22041)	commit \| commitdiff \| tree
2026-04-19	Sigbjørn Skjæret	ci : install spirv-headers for vulkan-cross (#22109)	commit \| commitdiff \| tree
2026-04-19	Dowon	convert : support sentence-transformer 5.4 config files...	commit \| commitdiff \| tree
2026-04-19	texasich	cmake: remove CMP0194 policy to restore MSVC builds...	commit \| commitdiff \| tree
2026-04-19	Sascha Rogmann	server : speculative checkpointing (#19493)	commit \| commitdiff \| tree
2026-04-19	Radoslav Gerganov	rpc : refactor the RPC transport (#21998)	commit \| commitdiff \| tree
2026-04-18	Cetarthoriphros	server: Expose `media_tag` on /props endpoint. (#22028)	commit \| commitdiff \| tree
2026-04-18	Sigbjørn Skjæret	model : refactor bias tensor variable names (#22079)	commit \| commitdiff \| tree
2026-04-18	Sigbjørn Skjæret	android : libcommon -> libllama-common (#22076)	commit \| commitdiff \| tree
2026-04-18	SamareshSingh	ggml-backend-meta: add multi-segment read support in...	commit \| commitdiff \| tree
2026-04-18	Sigbjørn Skjæret	ci : free disk space for rocm release (#22012)	commit \| commitdiff \| tree
2026-04-18	Sigbjørn Skjæret	convert : fix (ignore for now) typings errors (#22002)	commit \| commitdiff \| tree
2026-04-18	Johannes Gäßler	llama: fit ctx size for CPU only (#21568)	commit \| commitdiff \| tree
2026-04-17	Reese Levine	ggml-webgpu: fix compiler warnings and refactor FlashAt...	commit \| commitdiff \| tree
2026-04-17	Aman Gupta	CUDA: use LRU based eviction for cuda graphs (#21611)	commit \| commitdiff \| tree
2026-04-17	Yuri Khrustalev	ci : add android arm64 build and release (#21647)	commit \| commitdiff \| tree
2026-04-17	65a	mtmd: add missing struct tag (#22023)	commit \| commitdiff \| tree
2026-04-17	Georgi Gerganov	libs : rename libcommon -> libllama-common (#21936)	commit \| commitdiff \| tree
2026-04-17	Eric Zhang	model : Gemma4 model type detection (#22027)	commit \| commitdiff \| tree
2026-04-17	lhez	opencl: refactor q8_0 set_tensor and mul_mat host side...	commit \| commitdiff \| tree
2026-04-16	Sigbjørn Skjæret	cli : use get_media_marker (#22017)	commit \| commitdiff \| tree
2026-04-16	Xuan-Son Nguyen	cmake: use glob to collect src/models sources (#22005)	commit \| commitdiff \| tree
2026-04-16	nullname	hexagon: optimize HMX matmul operations (#21071)	commit \| commitdiff \| tree
2026-04-16	Xuan-Son Nguyen	model: using single llm_build per arch (#21970)	commit \| commitdiff \| tree
2026-04-16	shaofeiqi	opencl: add q5_K gemm and gemv kernels for Adreno ...	commit \| commitdiff \| tree
2026-04-16	Pascal	server: tests: fetch random media marker via /apply...	commit \| commitdiff \| tree
2026-04-16	PikaPikachu	model : refactor QKV into common build_qkv and create_t...	commit \| commitdiff \| tree
2026-04-16	Sigbjørn Skjæret	model : support NVFP4 tensors for Gemma4 (#21971)	commit \| commitdiff \| tree
2026-04-16	Ruben Ortlam	codeowners: add team member comments (#21714)	commit \| commitdiff \| tree
2026-04-16	Anav Prasad	Convert: Fix NemotronH Config Parsing (#21664)	commit \| commitdiff \| tree
2026-04-16	Aman Gupta	ggml: add graph_reused (#21764)	commit \| commitdiff \| tree
2026-04-16	Kusha Gharahi	metal: Implement ROLL op (#21946)	commit \| commitdiff \| tree
2026-04-16	rehan-10xengineer	ggml-cpu: add 128-bit RVV implementation for Quantizati...	commit \| commitdiff \| tree
2026-04-16	rehan-10xengineer	ggml : implemented simd_gemm kernel for riscv vector...	commit \| commitdiff \| tree
2026-04-16	Yuannan	devops : added spirv-headers to nix (#21965)	commit \| commitdiff \| tree
2026-04-16	Reese Levine	ggml-webgpu: compute pass batching and removing profili...	commit \| commitdiff \| tree
2026-04-16	Ludovic Henry	ci : Use ggml-org/ccache-action on RISC-V as well ...	commit \| commitdiff \| tree
2026-04-16	Katostrofik	[SYCL] Fix Q8_0 reorder: garbage on 2nd prompt + crash...	commit \| commitdiff \| tree
2026-04-15	Xuan-Son Nguyen	server: use random media marker (#21962)	commit \| commitdiff \| tree
2026-04-15	Ruben Ortlam	vulkan: optimize im2col (#21713)	commit \| commitdiff \| tree
2026-04-15	Pasha Khosravi	cuda: Q1_0 initial backend (#21629)	commit \| commitdiff \| tree
2026-04-15	Reese Levine	ggml-webgpu: Fix dequantization helpers to not pass...	commit \| commitdiff \| tree
2026-04-15	Johannes Gäßler	CUDA: require explicit opt-in for P2P access (#21910)	commit \| commitdiff \| tree
2026-04-15	Johannes Gäßler	CUDA: manage NCCL communicators in context (#21891)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom