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

2025-07-19	compilade	imatrix : use GGUF to store importance matrices (#9400)	commit \| commitdiff \| tree
2025-07-19	Peter0x44	vulkan: Add logging for bf16 features to ggml_vk_print_...	commit \| commitdiff \| tree
2025-07-19	0cc4m	Vulkan: Fix fprintf format-security warning (#14770)	commit \| commitdiff \| tree
2025-07-19	rspOverflow	Documentation: Update build.md's Vulkan section (#14736)	commit \| commitdiff \| tree
2025-07-19	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	metal : fuse add, mul + add tests (#14596)	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	graph : fix graph reuse reset of params (#14760)	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	parallel : add option for different RNG seeds (#14757)	commit \| commitdiff \| tree
2025-07-18	Oliver Simons	cuda : Fix Gemma3n not executed as CUDA_GRAPH on NVGPUs...	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	graph : avoid huge warm-up graphs for MoE models (...	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	model : fix build after merge conflict (#14754)	commit \| commitdiff \| tree
2025-07-18	lgai-exaone	model : add EXAONE 4.0 support (#14630)	commit \| commitdiff \| tree
2025-07-18	Aman Gupta	CUDA: set_rows + cpy.cu refactor (#14712)	commit \| commitdiff \| tree
2025-07-18	Georgi Gerganov	graph : refactor context to not pass gf explicitly...	commit \| commitdiff \| tree
2025-07-18	Nexes the Elder	graph : Pass the graph placeholder message in debug...	commit \| commitdiff \| tree
2025-07-18	Neo Zhang Jianyu	use max work group size for device to replace the magic...	commit \| commitdiff \| tree
2025-07-17	Piotr Wilkin...	convert : fix Ernie4.5 MoE without shared experts ...	commit \| commitdiff \| tree
2025-07-17	Wroclaw	nix : use optionalAttrs for env mkDerivation attrset...	commit \| commitdiff \| tree
2025-07-17	Piotr Wilkin...	model: add Ernie 4.5 MoE support (#14658)	commit \| commitdiff \| tree
2025-07-17	Georgi Gerganov	kv-cache : fix k-shift for multiple streams (#14742)	commit \| commitdiff \| tree
2025-07-17	Georgi Gerganov	llama : reuse compute graphs (#14482)	commit \| commitdiff \| tree
2025-07-17	Tarek Dakhran	llama : fix parallel processing for lfm2 (#14705)	commit \| commitdiff \| tree
2025-07-17	Georgi Gerganov	kv-cache : opt mask set input (#14600)	commit \| commitdiff \| tree
2025-07-17	Georgi Gerganov	batch : fix uninitialized has_cpl flag (#14733)	commit \| commitdiff \| tree
2025-07-16	Sigbjørn Skjæret	ci : disable failing vulkan crossbuilds (#14723)	commit \| commitdiff \| tree
2025-07-16	Sigbjørn Skjæret	convert : make hf token optional (#14717)	commit \| commitdiff \| tree
2025-07-16	Diner Burger	llama : fix parameter order for hybrid memory initializ...	commit \| commitdiff \| tree
2025-07-16	Reese Levine	ggml: Add initial WebGPU backend (#14521)	commit \| commitdiff \| tree
2025-07-16	tempstudio	model : support output bias for qwen2 (#14711)	commit \| commitdiff \| tree
2025-07-16	Georgi Gerganov	llama : add high-throughput mode (#14363)	commit \| commitdiff \| tree
2025-07-16	Aman Gupta	Support diffusion models: Add Dream 7B (#14644)	commit \| commitdiff \| tree
2025-07-16	Georgi Gerganov	ggml : add asserts (#14720)	commit \| commitdiff \| tree
2025-07-16	Georgi Gerganov	server : pre-calculate EOG logit biases (#14721)	commit \| commitdiff \| tree
2025-07-16	Shunta Saito	llama : fix parallel processing for plamo2 (#14716)	commit \| commitdiff \| tree
2025-07-16	Georgi Gerganov	server : fix handling of the ignore_eos flag (#14710)	commit \| commitdiff \| tree
2025-07-16	Johannes Gäßler	scripts: synthetic prompt mode for server-bench.py...	commit \| commitdiff \| tree
2025-07-16	Sigbjørn Skjæret	convert : only check for tokenizer folder if we need...	commit \| commitdiff \| tree
2025-07-16	Sigbjørn Skjæret	convert : add pre-computed hashes first to prevent...	commit \| commitdiff \| tree
2025-07-16	Min-Hua	llama: add LLAMA_API to deprecated llama_kv_self_seq_di...	commit \| commitdiff \| tree
2025-07-15	Ed Addario	gguf-py : dump bpw per layer and model in markdown...	commit \| commitdiff \| tree
2025-07-15	Gabriel Larson	model : add Kimi-K2 support (#14654)	commit \| commitdiff \| tree
2025-07-15	Jeff Bolz	vulkan: fix noncontig check for mat_mul_id splitting...	commit \| commitdiff \| tree
2025-07-15	Jeff Bolz	vulkan: add RTE variants for glu/add/sub/mul/div (...	commit \| commitdiff \| tree
2025-07-15	Shunta Saito	model : add PLaMo-2 support (#14560)	commit \| commitdiff \| tree
2025-07-15	R0CKSTAR	cuda: fix build warnings in set-rows.cu (unused variabl...	commit \| commitdiff \| tree
2025-07-14	Anton Mitkov	sycl: Hotfix for non dnnl codepath (#14677)	commit \| commitdiff \| tree
2025-07-14	shalinib-ibm	ggml : refactor llamafile_sgemm PPC code (#14673)	commit \| commitdiff \| tree
2025-07-14	Aman Gupta	llama-context: add ability to get logits (#14672)	commit \| commitdiff \| tree
2025-07-14	Johannes Gäßler	scripts: benchmark for HTTP server throughput (#14668)	commit \| commitdiff \| tree
2025-07-14	Akarshan Biswas	SYCL: use 1D kernel for set_rows (#14618)	commit \| commitdiff \| tree
2025-07-14	Anton Mitkov	sycl: Batched mulmat rework for oneDNN dispatch (#14617)	commit \| commitdiff \| tree
2025-07-13	Molly Sophia	llama : add jinja template for rwkv-world (#14665)	commit \| commitdiff \| tree
2025-07-13	Ed Addario	quantize : fix minor logic flaw in --tensor-type (...	commit \| commitdiff \| tree
2025-07-13	Sigbjørn Skjæret	cuda : add set rows for bf16 (#14664)	commit \| commitdiff \| tree
2025-07-13	Yavor Ivanov	cuda : add ELU support (#14657)	commit \| commitdiff \| tree
2025-07-13	Georgi Gerganov	ggml : add build-time message to remind about ggml_set_...	commit \| commitdiff \| tree
2025-07-13	Yavor Ivanov	metal : Add missing unary ops Metal support (#14660)	commit \| commitdiff \| tree
2025-07-13	Yavor Ivanov	cmake : Add CMake presets for Linux and GCC (#14656)	commit \| commitdiff \| tree
2025-07-12	Tarek Dakhran	tests : cover lfm2 cases in test_ssm_conv (#14651)	commit \| commitdiff \| tree
2025-07-12	Tarek Dakhran	docs : add LFM2 to models section (#14650)	commit \| commitdiff \| tree
2025-07-12	Aman Gupta	CUDA: add set rows for f32 and f16 (#14551) upstream/0.0.5882	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	vulkan : remove unused vars (#0)	commit \| commitdiff \| tree
2025-07-12	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
2025-07-12	Acly	vulkan : implement bilinear interpolation (ggml/1291)	commit \| commitdiff \| tree
2025-07-12	Acly	vulkan : implement ggml_roll (ggml/1290)	commit \| commitdiff \| tree
2025-07-12	Douglas Hanley	server : fix pooled embedding output (#14645)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: support SET_ROWS (#14587)	commit \| commitdiff \| tree
2025-07-12	Jeff Bolz	vulkan: optimizations for deepseek prompt processing...	commit \| commitdiff \| tree
2025-07-11	Tarek Dakhran	model : support LiquidAI LFM2 hybrid family (#14620)	commit \| commitdiff \| tree
2025-07-11	Slobodan Josic	HIP : Add HIP 7.0+ compatibility for hipBLAS compute...	commit \| commitdiff \| tree
2025-07-11	Georgi Gerganov	readme : add hot PRs (#14636)	commit \| commitdiff \| tree
2025-07-11	Georgi Gerganov	llama : move enum llama_vocab_pre_type to implementatio...	commit \| commitdiff \| tree
2025-07-11	Dowon	vocab : add midm-2.0 model pre-tokenizer (#14626)	commit \| commitdiff \| tree
2025-07-11	Gabe Goodhart	model : Granite Four (#13550)	commit \| commitdiff \| tree
2025-07-10	rmatif	opencl: add tiled mul_mat_f16_f32 (#14535)	commit \| commitdiff \| tree
2025-07-10	lhez	opencl: add `set_rows` for `f16` and `f32` (#14547)	commit \| commitdiff \| tree
2025-07-10	Ryan Mangeno	Smoldocling support (#14597)	commit \| commitdiff \| tree
2025-07-10	Aman Gupta	Docs: script to auto-generate ggml operations docs...	commit \| commitdiff \| tree
2025-07-10	Eric Zhang	cmake : do not search for curl libraries by ourselves...	commit \| commitdiff \| tree
2025-07-10	Akarshan Biswas	SYCL: Initial set_rows kernel implementation (#14562)	commit \| commitdiff \| tree
2025-07-10	Xuan-Son Nguyen	llama : minor coding style fix for smollm3 (#14605)	commit \| commitdiff \| tree
2025-07-10	Eric Zhang	cmake : bump llguidance version to v1.0.1 (#14609)	commit \| commitdiff \| tree
2025-07-10	Eric Zhang	cmake : llguidance build parser library only (#14608)	commit \| commitdiff \| tree
2025-07-10	compilade	cuda : support Falcon-H1 state size for SSM_SCAN (...	commit \| commitdiff \| tree
2025-07-09	Xuan-Son Nguyen	llama : remove llm_graph_input_one (#14603)	commit \| commitdiff \| tree
2025-07-09	compilade	llama : support Jamba hybrid Transformer-Mamba models...	commit \| commitdiff \| tree
2025-07-09	Xuan-Son Nguyen	ggml : add ggml_scale_bias (#14417)	commit \| commitdiff \| tree
2025-07-09	Miaoqian Lin	ggml : prevent integer overflow in gguf tensor size...	commit \| commitdiff \| tree
2025-07-09	Dowon	model : add skt/A.X-4.0 model vocabulary (#14589)	commit \| commitdiff \| tree
2025-07-09	Sigbjørn Skjæret	llama : remove unintended whitespace (#14592)	commit \| commitdiff \| tree
2025-07-09	ibrahim khadraoui	model : add support for Falcon-H1 family (#14534)	commit \| commitdiff \| tree
2025-07-09	Xuan-Son Nguyen	convert : fix smollm3 jinja template (#14586)	commit \| commitdiff \| tree
2025-07-08	Jeff Bolz	vulkan: optimize flash attention split_k_reduce (#14554)	commit \| commitdiff \| tree
2025-07-08	stevenkuang	model : fix hunyuan moe chat template (#14584)	commit \| commitdiff \| tree
2025-07-08	Xuan-Son Nguyen	model : add SmolLM3 (#14581)	commit \| commitdiff \| tree
2025-07-08	compilade	memory : fix broken batch splits for recurrent cache...	commit \| commitdiff \| tree
2025-07-08	Jeff Bolz	vulkan : fix rope with partial rotation and non-cont...	commit \| commitdiff \| tree
2025-07-08	Alawode Oluwandabira	server: Add ability to mount server at prefix (#14544)	commit \| commitdiff \| tree
2025-07-08	Xuan-Son Nguyen	model : add hunyuan moe (#14425)	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom