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

2025-04-18	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
2025-04-16	Chenguang Li	CANN: Add 310P operator support check (#12962)	commit \| commitdiff \| tree
2025-04-15	lhez	opencl: split `ggml-opencl.cl` into multiple files...	commit \| commitdiff \| tree
2025-04-15	Georgi Gerganov	metal : add FA-vec kernels for head size 96 (#12952)	commit \| commitdiff \| tree
2025-04-15	hipudding	CANN: Add x86 build ci (#12950)	commit \| commitdiff \| tree
2025-04-15	David Huang	CUDA/HIP: Share the same unified memory allocation...	commit \| commitdiff \| tree
2025-04-15	Akarshan Biswas	SYCL: Add ROPE vision kernel (#12887)	commit \| commitdiff \| tree
2025-04-15	Juk Armstrong	llama : DeepSeek V2/V3 MLA implementation (#12801)	commit \| commitdiff \| tree
2025-04-15	Srihari-mcw	ggml : Add AVX512 implementation of GEMM - Q4_Kx8 ...	commit \| commitdiff \| tree
2025-04-15	Chenguang Li	CANN: Opt ROPE optimization (#12865)	commit \| commitdiff \| tree
2025-04-15	Xinpeng Dou	CANN: Optimize CANN buffer pool memory management ...	commit \| commitdiff \| tree
2025-04-14	Russyyds	Add performance print for gemma3 in example (#12929)	commit \| commitdiff \| tree
2025-04-14	Akarshan Biswas	SYCL: Fix im2col (#12910)	commit \| commitdiff \| tree
2025-04-14	Radoslav Gerganov	rpc : use ggml_context_ptr (#12938)	commit \| commitdiff \| tree
2025-04-14	Neo Zhang Jianyu	dsiable curl lib check, this action is missed by commit...	commit \| commitdiff \| tree
2025-04-14	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-04-14	cmdr2	cpu: fix cpu backend's supports-op for GET_ROWS_BACK...	commit \| commitdiff \| tree
2025-04-14	SXX	ggml: use _mm[512/256]_dpbusd[_avx]_epi32 to directly...	commit \| commitdiff \| tree
2025-04-13	Alan Gray	ggml: disable CUDA graphs for unsupported DUP and CONT...	commit \| commitdiff \| tree
2025-04-13	Ed Addario	quantize: Handle user-defined quantization levels for...	commit \| commitdiff \| tree
2025-04-12	Prajwal B Mehendarkar	common : Define cache directory on AIX (#12915)	commit \| commitdiff \| tree
2025-04-12	Jeff Bolz	vulkan: use aligned loads for flash attention mask...	commit \| commitdiff \| tree
2025-04-12	Matt Clayton	llava: Fix cpu-only clip image encoding sefault (#12907)	commit \| commitdiff \| tree
2025-04-11	Georgi Gerganov	server : add VSCode's Github Copilot Chat support ...	commit \| commitdiff \| tree
2025-04-11	yuri@FreeBSD	rpc : Set cache directory in rpc-server.cpp on FreeBSD...	commit \| commitdiff \| tree
2025-04-11	Olivier Chafik	`tool-call`: fix non-tool-calling grammar crashes w...	commit \| commitdiff \| tree
2025-04-11	yuri@FreeBSD	common : Define cache directory on FreeBSD (#12892)	commit \| commitdiff \| tree
2025-04-11	Ewan Crawford	sycl: Support sycl_ext_oneapi_limited_graph (#12873)	commit \| commitdiff \| tree
2025-04-11	tastelikefeet	contrib: support modelscope community (#12664)	commit \| commitdiff \| tree
2025-04-11	Yuxuan Zhang	llama-model : add Glm4Model implementation for GLM...	commit \| commitdiff \| tree
2025-04-11	Xuan-Son Nguyen	clip : use smart pointer (⚠️ breaking change) (#12869)	commit \| commitdiff \| tree
2025-04-11	Akarshan Biswas	SYCL: Add fp16 type support to unary op kernels (#12788)	commit \| commitdiff \| tree
2025-04-11	Daniel Han	convert : Llama4 RoPE fix (#12889)	commit \| commitdiff \| tree
2025-04-11	R0CKSTAR	ci : Replace freediskspace to free_disk_space in docker...	commit \| commitdiff \| tree
2025-04-11	Daniel Bevenius	xcf : add check for visionos build version (#12854)	commit \| commitdiff \| tree
2025-04-11	Xuan-Son Nguyen	convert : proper tensor name mapping for llama4 (#12870)	commit \| commitdiff \| tree
2025-04-11	Xuan-Son Nguyen	llama : correct rms norm for llama 4 (#12882)	commit \| commitdiff \| tree
2025-04-11	Aaron Teo	ggml: fix compilation error s390x (#12848)	commit \| commitdiff \| tree
2025-04-10	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-04-10	Georgi Gerganov	tests : fix init order (#0)	commit \| commitdiff \| tree
2025-04-10	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-04-10	cmdr2	ggml: don't include arm_neon.h when using CUDA 12 with...	commit \| commitdiff \| tree
2025-04-10	Diego Devesa	ggml : add bilinear upscale support (ggml/1185)	commit \| commitdiff \| tree
2025-04-10	Diego Devesa	ggml : add more generic custom op, remove deprecated...	commit \| commitdiff \| tree
2025-04-10	Georgi Gerganov	scripts : fix sync-ggml-am.sh	commit \| commitdiff \| tree
2025-04-10	Xuan-Son Nguyen	llava : introduce libmtmd (#12849)	commit \| commitdiff \| tree
2025-04-10	Xuan-Son Nguyen	convert : ability to lazy-load safetensors remotely...	commit \| commitdiff \| tree
2025-04-10	Chenguang Li	CANN: Support more ops (#12841)	commit \| commitdiff \| tree
2025-04-09	Prajwal B Mehendarkar	Fixes #12823 (#12830)	commit \| commitdiff \| tree
2025-04-09	Rudi Servo	docker : added all CPU to GPU images (#12749)	commit \| commitdiff \| tree
2025-04-09	Piotr Kubaj	ggml-cpu-impl.h: do not redefine bool on POWER9 (#12856)	commit \| commitdiff \| tree
2025-04-09	Piotr Kubaj	ggml-impl.h: fix build on POWER9 (#12855)	commit \| commitdiff \| tree
2025-04-09	Bo Zheng	llama : Support Qwen3 and Qwen3MoE (#12828)	commit \| commitdiff \| tree
2025-04-09	R0CKSTAR	musa: enable freediskspace for docker image build ...	commit \| commitdiff \| tree
2025-04-09	Romain Biessy	sycl: update documentation to use -no-cnv (#12845)	commit \| commitdiff \| tree
2025-04-09	Plamen Minev	ci: detach common from the library (#12827)	commit \| commitdiff \| tree
2025-04-09	Xuan-Son Nguyen	clip : do not print ftype (#12832)	commit \| commitdiff \| tree
2025-04-09	Georgi Gerganov	readme : add rpc backend (#12842)	commit \| commitdiff \| tree
2025-04-09	Chenguang Li	CANN: Support Opt CONV_TRANSPOSE_1D and ELU (#12786)	commit \| commitdiff \| tree
2025-04-09	Jeff Bolz	vulkan: In coopmat2 mmq, load q4_k/q5_k scales through...	commit \| commitdiff \| tree
2025-04-09	Jeff Bolz	vulkan: Use fp16 for the flash attention P*V multiplica...	commit \| commitdiff \| tree
2025-04-08	Sigbjørn Skjæret	cuda : add f32 to bf16 copy op (#12806)	commit \| commitdiff \| tree
2025-04-08	Matt Clayton	llava: improve clip_ctx destructor to not memleak load_...	commit \| commitdiff \| tree
2025-04-08	Georgi Gerganov	llama : fix FA when KV cache is not used (i.e. embeddin...	commit \| commitdiff \| tree
2025-04-08	Xuan-Son Nguyen	server : fix thread.join() on exit (#12831)	commit \| commitdiff \| tree
2025-04-08	dm4	llava: add more helper functions to check projector...	commit \| commitdiff \| tree
2025-04-08	Prajwal B Mehendarkar	arg : Including limits file on AIX (#12822)	commit \| commitdiff \| tree
2025-04-08	characharm	server : webui : Improve Chat Input with Auto-Sizing...	commit \| commitdiff \| tree
2025-04-08	Neo Zhang Jianyu	Revert "sycl:remove redundant memcopy in function ggml_...	commit \| commitdiff \| tree
2025-04-08	compilade	gguf-py : support lazy tensor splitting (#12809)	commit \| commitdiff \| tree
2025-04-07	Xuan-Son Nguyen	llama : Support llama 4 text-only (#12791)	commit \| commitdiff \| tree
2025-04-07	lhez	opencl: better identify Adreno GPU (#12760)	commit \| commitdiff \| tree
2025-04-07	stduhpf	hellaswag: display estimated score confidence interval...	commit \| commitdiff \| tree
2025-04-07	Georgi Gerganov	cuda : fix HIP and MUSA BF16 (#0)	commit \| commitdiff \| tree
2025-04-07	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-04-07	Georgi Gerganov	ggml : simplify Arm fp16 CPU logic (ggml/1177)	commit \| commitdiff \| tree
2025-04-07	Sigbjørn Skjæret	CUDA: don't convert BF16 weights to FP32 (ggml/1174)	commit \| commitdiff \| tree
2025-04-07	cmdr2	cpu: move all the operators into a separate c++ file...	commit \| commitdiff \| tree
2025-04-07	zhouwg	sycl: remove redundant memcopy in function ggml_backend...	commit \| commitdiff \| tree
2025-04-07	Xuan-Son Nguyen	ci : no curl on ggml-ci (#12796)	commit \| commitdiff \| tree
2025-04-07	Xuan-Son Nguyen	cmake : enable curl by default (#12761)	commit \| commitdiff \| tree
2025-04-07	zhouwg	CANN: fix typo in ggml-cann (#12733)	commit \| commitdiff \| tree
2025-04-07	hipudding	CANN: Refactor to reduce duplicate code (#12731)	commit \| commitdiff \| tree
2025-04-06	R0CKSTAR	musa: fix compilation warnings in mp_22/31 (#12780)	commit \| commitdiff \| tree
2025-04-06	Jeff Bolz	vulkan: fix NaN issue in flash attention shader (#12776)	commit \| commitdiff \| tree
2025-04-06	Jeff Bolz	vulkan: Use unclamped loads for flash attention mask...	commit \| commitdiff \| tree
2025-04-05	0cc4m	Vulkan: Tune Vulkan mmq int dot shader for performance...	commit \| commitdiff \| tree
2025-04-05	Sergey Fedorov	common : fix includes in arg.cpp and gemma3-cli.cpp...	commit \| commitdiff \| tree
2025-04-05	Xuan-Son Nguyen	clip : refactor clip_init, add tests (#12757)	commit \| commitdiff \| tree
2025-04-05	エシュナヴァリシア	common: custom hf endpoint support (#12769)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom