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

2025-05-01	Xuan-Son Nguyen	mtmd : add vision support for Mistral Small 3.1...	commit \| commitdiff \| tree
2025-05-01	Xuan-Son Nguyen	arg : remove CURLINFO_EFFECTIVE_METHOD (#13228)	commit \| commitdiff \| tree
2025-05-01	Jared Van Bortel	llama-model : fix the reported size class for nomic...	commit \| commitdiff \| tree
2025-05-01	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-05-01	Diego Devesa	ggml : fix ggml_gallocr_ptr type (ggml/1205)	commit \| commitdiff \| tree
2025-05-01	Georgi Gerganov	cuda : fix unused variable compile warning (whisper/0)	commit \| commitdiff \| tree
2025-04-30	Johannes Gäßler	CUDA: batched+noncont MMQ, refactor bs>1 MoE code ...	commit \| commitdiff \| tree
2025-04-30	Xuan-Son Nguyen	arg : -hf do not fail if url mismatch (#13219)	commit \| commitdiff \| tree
2025-04-30	ddh0	fix typo: `n_ctx_pre_seq` -> `n_ctx_per_seq` (#13221)	commit \| commitdiff \| tree
2025-04-30	Xuan-Son Nguyen	convert : improve model arch handling (#13122)	commit \| commitdiff \| tree
2025-04-30	Tatsuya Tanaka	llava : remove duplicate include (#13207)	commit \| commitdiff \| tree
2025-04-30	Olivier Chafik	common : add -jf / --json-schema-file flag (#12011)	commit \| commitdiff \| tree
2025-04-30	Jeff Bolz	vulkan: use uint array index to avoid glslang bug ...	commit \| commitdiff \| tree
2025-04-30	shalinib-ibm	ggml : fix ppc64le build (#13176)	commit \| commitdiff \| tree
2025-04-30	Xuan-Son Nguyen	convert : correct typo image_mean --> image_std (#13208)	commit \| commitdiff \| tree
2025-04-30	Aaron Teo	feat(ggml-cpu): enable z17 compile (#13182)	commit \| commitdiff \| tree
2025-04-30	Xuan-Son Nguyen	arg : allow using -hf offline (#13202)	commit \| commitdiff \| tree
2025-04-30	Xuan-Son Nguyen	docker : do not build tests (#13204)	commit \| commitdiff \| tree
2025-04-30	xiaofei	rpc : fix cache directory initialization (#13188)	commit \| commitdiff \| tree
2025-04-29	Johannes Gäßler	scripts: n_depth for compare-llama-bench [no ci] (...	commit \| commitdiff \| tree
2025-04-29	matteo	server : Prefilling assistant message in openai compati...	commit \| commitdiff \| tree
2025-04-29	Georgi Gerganov	sampling : when top-k <= 0 -> noop (#13173)	commit \| commitdiff \| tree
2025-04-29	Alberto Cabrera...	llama-bench: fixed size of fields to correctly map...	commit \| commitdiff \| tree
2025-04-29	Johannes Gäßler	CUDA: fix non-cont. inputs for batched mat mul (#13155)	commit \| commitdiff \| tree
2025-04-29	Sigbjørn Skjæret	llama : llm_type order by size (#13177)	commit \| commitdiff \| tree
2025-04-29	Xuan-Son Nguyen	mtmd : add qwen2vl and qwen2.5vl (#13141)	commit \| commitdiff \| tree
2025-04-29	Sigbjørn Skjæret	llama : set qwen3 model type sizes (#13175)	commit \| commitdiff \| tree
2025-04-29	Xuan-Son Nguyen	llama-graph : fix text position for mrope (#13159)	commit \| commitdiff \| tree
2025-04-28	AT	model : Nomic Embed Text V2 with Mixture-of-Experts...	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	clip : fix model size display (#13153)	commit \| commitdiff \| tree
2025-04-28	Ville Vesilehto	fix(rpc): Improve input validation and error handling...	commit \| commitdiff \| tree
2025-04-28	Vishal Agarwal	llama-bench: add `-d` depth arg (#13096)	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	mtmd : fix glm-edge redundant token count (#13139)	commit \| commitdiff \| tree
2025-04-28	pockers21	context : do not clear output buffer on reserve (#13152)	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	llama : (mrope) allow using normal 1D position for...	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	clip : refactor set input for cgraph + fix qwen2.5vl...	commit \| commitdiff \| tree
2025-04-28	Akarshan Biswas	SYCL: Add all missing unary kernels (#13074)	commit \| commitdiff \| tree
2025-04-28	Georgi Gerganov	readme : update hot topics (#13150)	commit \| commitdiff \| tree
2025-04-28	Georgi Gerganov	common : fix noreturn compile warning (#13151)	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	llama-chat : fix typo GML --> GLM (#13143)	commit \| commitdiff \| tree
2025-04-28	R0CKSTAR	musa: fix typo in cc control (#13144)	commit \| commitdiff \| tree
2025-04-28	Johannes Gäßler	CUDA: fix q_nope_absorbed prec for DS 2 Lite f16 (...	commit \| commitdiff \| tree
2025-04-28	Xuan-Son Nguyen	arg : fix unused variable (#13142)	commit \| commitdiff \| tree
2025-04-27	4onen	llama-bench : Add `--override-tensors` arg (#12922)	commit \| commitdiff \| tree
2025-04-27	matteo	llama-chat : fix wrong template in GLM4-0414 (#13140)	commit \| commitdiff \| tree
2025-04-27	R0CKSTAR	musa: fix build warning (#13129)	commit \| commitdiff \| tree
2025-04-27	LostRuins Concedo	Fixes Qwen2.5VL segfault during inference with https...	commit \| commitdiff \| tree
2025-04-27	HimariO	clip : Add Qwen2.5VL support (#12402)	commit \| commitdiff \| tree
2025-04-26	Xuan-Son Nguyen	common : add common_remote_get_content (#13123)	commit \| commitdiff \| tree
2025-04-26	Xuan-Son Nguyen	clip : improve projector naming (#13118)	commit \| commitdiff \| tree
2025-04-26	SXX	ggml: move fp16/bf16 conversion optimizations to CPU...	commit \| commitdiff \| tree
2025-04-26	frob	grammar : handle maxItems == 0 in JSON schema (#13117)	commit \| commitdiff \| tree
2025-04-25	Diego Devesa	llama : fix K-shift with quantized K and BLAS backend...	commit \| commitdiff \| tree
2025-04-25	City	Force FP32 compute in GLM4 FFN Down (#13101)	commit \| commitdiff \| tree
2025-04-25	Xuan-Son Nguyen	clip : fix pixtral on some GPU backends (#13097)	commit \| commitdiff \| tree
2025-04-25	Neo Zhang Jianyu	change the reorder tensor from init to execute OP ...	commit \| commitdiff \| tree
2025-04-25	Radoslav Gerganov	rpc : do not wait for response when sending RPC_CMD_SET...	commit \| commitdiff \| tree
2025-04-24	Xuan-Son Nguyen	clip : remove boi/eoi embeddings for GLM-edge model...	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	embeddings : fix batch sizes (#13076) upstream/0.0.5185	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	ggml : fix trailing whitespaces (#0)	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-04-24	Acly	ggml : Depthwise 2D convolution (ggml/1152)	commit \| commitdiff \| tree
2025-04-24	Johannes Gäßler	CUDA: use switch statements in constexpr functions...	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	cmake : do not include ./src as public for libllama...	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	clang-tidy : disable warning about missing math parenth...	commit \| commitdiff \| tree
2025-04-24	Xuan-Son Nguyen	arg : add --no-mmproj-offload (#13093)	commit \| commitdiff \| tree
2025-04-24	Xuan-Son Nguyen	arg : clean up handling --mmproj with -hf (#13082)	commit \| commitdiff \| tree
2025-04-24	Georgi Gerganov	metal : fix floating-point range of attention scores...	commit \| commitdiff \| tree
2025-04-24	Eve	vulkan: matmul gcn tuning (#13016)	commit \| commitdiff \| tree
2025-04-23	pl752	llama-mtmd-cli: Sigint rework in mtmd vision example...	commit \| commitdiff \| tree
2025-04-23	Xuan-Son Nguyen	mtmd : Support Pixtral 12B (#13065)	commit \| commitdiff \| tree
2025-04-23	piDack	convert : Append mult-eos,half-rope,bos to GLM4-0414...	commit \| commitdiff \| tree
2025-04-23	Radoslav Gerganov	rpc : add command line option for number of threads...	commit \| commitdiff \| tree
2025-04-22	Johannes Gäßler	CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014)	commit \| commitdiff \| tree
2025-04-22	Xuan-Son Nguyen	mtmd : support SmolVLM (version 1 and 2) (#13050)	commit \| commitdiff \| tree
2025-04-22	Georgi Gerganov	security : add note about RPC and server functionality...	commit \| commitdiff \| tree
2025-04-22	Georgi Gerganov	metal : add memory pool for temp allocs (#12850)	commit \| commitdiff \| tree
2025-04-22	Xuan-Son Nguyen	llava : update documentations (#13055)	commit \| commitdiff \| tree
2025-04-21	Diego Devesa	ggml : add SSE 4.2 and x64 base variant for CPUs withou...	commit \| commitdiff \| tree
2025-04-21	Akarshan Biswas	SYCL: Add non-contiguous support in ROPE (#12993)	commit \| commitdiff \| tree
2025-04-21	Xuan-Son Nguyen	mtmd : merge llava, gemma3 and minicpmv CLI into single...	commit \| commitdiff \| tree
2025-04-20	Xuan-Son Nguyen	convert : experimental support for `--mmproj` flag...	commit \| commitdiff \| tree
2025-04-20	Jeffrey Morgan	llava: fix errors in clip.h on certain compilers (...	commit \| commitdiff \| tree
2025-04-20	Jeff Bolz	vulkan: support noncontiguous rms_norm (#13031)	commit \| commitdiff \| tree
2025-04-20	Jeffrey Morgan	metal: add neg operator (#13029)	commit \| commitdiff \| tree
2025-04-19	bandoti	Disable CI cross-compile builds (#13022)	commit \| commitdiff \| tree
2025-04-19	Sigbjørn Skjæret	gguf-py : fix upload python package workflow (#13020) gguf-v0.16.2	commit \| commitdiff \| tree
2025-04-19	Xuan-Son Nguyen	clip : refactor, add `image_manipulation` and `llava_uh...	commit \| commitdiff \| tree
2025-04-18	Daniel Tang	main : Fix Ctrl+D/newline handling (#12951)	commit \| commitdiff \| tree
2025-04-18	Chris Thompson	gguf-py : GGUF Editor GUI - Python + Qt6 (#12930) gguf-v0.16.1	commit \| commitdiff \| tree
2025-04-18	Xuan-Son Nguyen	server : use std::move whenever possible (#12936)	commit \| commitdiff \| tree
2025-04-18	Akarshan Biswas	SYCL: Refactor and enable FP16 in binary broadcast...	commit \| commitdiff \| tree
2025-04-18	Xuan-Son Nguyen	mtmd : add methods to access `mtmd_image_tokens` (...	commit \| commitdiff \| tree
2025-04-18	Radoslav Gerganov	rpc : add RPC_CMD_HELLO (#12955)	commit \| commitdiff \| tree
2025-04-17	Georgi Gerganov	graph : make FA compatible with MLA + add initial Metal...	commit \| commitdiff \| tree
2025-04-17	Alan Gray	ggml: Re-enable CUDA graphs in presence of CONT and...	commit \| commitdiff \| tree
2025-04-17	hipudding	CANN: Add support for async operator submission (#12864)	commit \| commitdiff \| tree
2025-04-17	Mikko Juola	llama : recognize IBM Granite 3.3 FIM tokens (#12988)	commit \| commitdiff \| tree
2025-04-16	kimminsu	opencl: fix incorrect local_size index in profiling...	commit \| commitdiff \| tree
2025-04-16	Jeff Bolz	vulkan: enable coopmat2 FA gqa and split_k optimization...	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom