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

2025-08-11	hipudding	CANN: Add broadcast for softmax and FA (#15208)	commit \| commitdiff \| tree
2025-08-11	rainred	mtmd : Fix MinicpmV model converter and clip to avoid...	commit \| commitdiff \| tree
2025-08-11	Xuan-Son Nguyen	chat : hotfix gpt-oss jinja raising an exception (...	commit \| commitdiff \| tree
2025-08-11	Xuan-Son Nguyen	server : allow specifying reasoning_format in HTTP...	commit \| commitdiff \| tree
2025-08-11	Zagaj	readme : update infra list (#15234)	commit \| commitdiff \| tree
2025-08-11	Georgi Gerganov	kv-cache : fix seq_rm with seq_id == -1 (#15226)	commit \| commitdiff \| tree
2025-08-11	Daniel Bevenius	kv-cache : log (debug) all streams in find_slot (#15176)	commit \| commitdiff \| tree
2025-08-11	Sigbjørn Skjæret	convert : fix merge conflicts (#15229)	commit \| commitdiff \| tree
2025-08-11	Daniel Bevenius	perplexity : update comments/error msg to use decode...	commit \| commitdiff \| tree
2025-08-11	Julien Denize	convert : improve Mistral models integration (#14737)	commit \| commitdiff \| tree
2025-08-11	Charles Xu	kleidiai: fix unsigned overflow bug (#15150)	commit \| commitdiff \| tree
2025-08-09	David Zhao	cuda: refactored ssm_scan and use CUB (#13291)	commit \| commitdiff \| tree
2025-08-09	Aman Gupta	CUDA: add attention sinks for tile and wmma (#15178)	commit \| commitdiff \| tree
2025-08-08	compilade	gguf-py : add Numpy MXFP4 de/quantization support ...	commit \| commitdiff \| tree
2025-08-08	Johannes Gäßler	server-bench: external OAI servers, sqlite (#15179)	commit \| commitdiff \| tree
2025-08-08	AN Long	ggml : fix field name when new ggml_backend (#14944)	commit \| commitdiff \| tree
2025-08-08	Olivier Chafik	vendor: sync minja (#15161)	commit \| commitdiff \| tree
2025-08-08	Johannes Gäßler	CUDA: attention sinks for mma FlashAttention (#15157)	commit \| commitdiff \| tree
2025-08-08	lhez	opencl: support sink in `soft_max` (attn sinks) (#15152)	commit \| commitdiff \| tree
2025-08-07	Xuan-Son Nguyen	convert : support non-mxfp4 HF model (#15153)	commit \| commitdiff \| tree
2025-08-07	Jeff Bolz	vulkan: support fattn sinks (#15126)	commit \| commitdiff \| tree
2025-08-07	Jeff Bolz	vulkan: Add env var to disable host visible vidmem...	commit \| commitdiff \| tree
2025-08-07	RunningLeon	llama : Support intern-s1 (#14875)	commit \| commitdiff \| tree
2025-08-07	uvos	HIP: add cmake option to enable compiler output of...	commit \| commitdiff \| tree
2025-08-07	Christian Kastner	ggml: Skip backend library linking code when GGML_BACKE...	commit \| commitdiff \| tree
2025-08-07	Johannes Gäßler	CUDA: GEMM for FP32/FP16/BF16 and ne11 <= 16 (#15131)	commit \| commitdiff \| tree
2025-08-07	Johannes Gäßler	scripts: fix crash when --tool is not set (#15133)	commit \| commitdiff \| tree
2025-08-07	Daniel Bevenius	requirements : fix PyTorch uint64 compatibility (#15134)	commit \| commitdiff \| tree
2025-08-06	Reese Levine	ggml: Add basic SET_ROWS support in WebGPU (#15137)	commit \| commitdiff \| tree
2025-08-06	rmatif	fix profiling crash (#15072)	commit \| commitdiff \| tree
2025-08-06	lhez	opencl: add `swiglu_oai` and `add_id` (#15121)	commit \| commitdiff \| tree
2025-08-06	Sachin Desai	chat : support Granite model reasoning and tool call...	commit \| commitdiff \| tree
2025-08-06	Juk Armstrong	Fixed name `-override-tensors` to `-override-tensor...	commit \| commitdiff \| tree
2025-08-06	Diego Devesa	ggml : fix fallback to CPU for ununsupported ops (...	commit \| commitdiff \| tree
2025-08-06	Sigbjørn Skjæret	chat : fix yandex chat template (#15116)	commit \| commitdiff \| tree
2025-08-06	stevenkuang	chat : fix hunyuan auto-detection (#15114)	commit \| commitdiff \| tree
2025-08-06	Chenguang Li	CANN: add support for ACL Graph (#15065)	commit \| commitdiff \| tree
2025-08-05	Reese Levine	ggml: WebGPU disable SET_ROWS for now (#15078)	commit \| commitdiff \| tree
2025-08-05	Georgi Gerganov	llama : add gpt-oss (#15091)	commit \| commitdiff \| tree
2025-08-05	Sigbjørn Skjæret	chat : only remove double bos/eos if added (#15086)	commit \| commitdiff \| tree
2025-08-05	Georgi Gerganov	readme : update hot topics (#15097)	commit \| commitdiff \| tree
2025-08-05	Romain Biessy	sycl: fix mul_mat selection (#15092)	commit \| commitdiff \| tree
2025-08-05	Juk Armstrong	Fix `glm4moe` bug (#15088)	commit \| commitdiff \| tree
2025-08-05	Alex Wu	webui: fix markdown table (#15081)	commit \| commitdiff \| tree
2025-08-05	compilade	context : fix index overflow on huge outputs (#15080)	commit \| commitdiff \| tree
2025-08-04	Diego Devesa	llama : add --n-cpu-moe option (#15077)	commit \| commitdiff \| tree
2025-08-04	compilade	imatrix : warn when GGUF imatrix is saved without ...	commit \| commitdiff \| tree
2025-08-04	Christian Kastner	cmake: Add GGML_BACKEND_DIR option (#15074)	commit \| commitdiff \| tree
2025-08-04	Sigbjørn Skjæret	gguf-py : add --chat-template-file to gguf_new_metadata...	commit \| commitdiff \| tree
2025-08-04	Sam	model: support GLM 4.5 family of models (#14939)	commit \| commitdiff \| tree
2025-08-04	Sigbjørn Skjæret	quantize : fix confusing error message if ftype is...	commit \| commitdiff \| tree
2025-08-04	Reese Levine	ggml: WebGPU backend host improvements and style fixing...	commit \| commitdiff \| tree
2025-08-04	Jeff Bolz	vulkan: fix build when using glslang that does not...	commit \| commitdiff \| tree
2025-08-03	compilade	imatrix : use GGUF by default (#14842)	commit \| commitdiff \| tree
2025-08-03	compilade	imatrix : fix 3d activation handling for hybrid and...	commit \| commitdiff \| tree
2025-08-03	compilade	memory : handle kv_unified for hybrid models (#15050)	commit \| commitdiff \| tree
2025-08-03	Csaba Kecskemeti	vocab : JetBrains Mellum pre-tokenizer (#15045)	commit \| commitdiff \| tree
2025-08-03	Gabriel Larson	model : add text-only support for Kimi-VL (and find...	commit \| commitdiff \| tree
2025-08-03	Jeff Bolz	vulkan: Use coopmat2 for conv2d (#14982)	commit \| commitdiff \| tree
2025-08-02	lhez	opencl: fix adreno compiler detection logic (#15029)	commit \| commitdiff \| tree
2025-08-02	Johannes Gäßler	CUDA: use mma FA kernel for gqa > 4 on RTX 4000 (#15035)	commit \| commitdiff \| tree
2025-08-02	leejet	cuda: make im2col a little faster (#15025) upstream/0.0.6073	commit \| commitdiff \| tree
2025-08-02	Daniel Bevenius	kv-cache : skip alignment of n_stream in kv-cache log...	commit \| commitdiff \| tree
2025-08-02	Georgi Gerganov	llama : enable LLAMA_SET_ROWS=1 by default (#14959)	commit \| commitdiff \| tree
2025-08-02	Georgi Gerganov	cuda, sycl : fix batched gemm when ne02 == 1 && ne03...	commit \| commitdiff \| tree
2025-08-02	Sigbjørn Skjæret	ci : check that pre-tokenizer hashes are up-to-date...	commit \| commitdiff \| tree
2025-08-02	Douglas Hanley	convert : fix Qwen3-Embedding pre-tokenizer hash (...	commit \| commitdiff \| tree
2025-08-02	Jhen-Jie Hong	chat : fix multiple tool_calls on hermes-2-pro (#14962)	commit \| commitdiff \| tree
2025-08-02	Jeff Bolz	vulkan: coopmat2 mul_mat optimizations (#14934)	commit \| commitdiff \| tree
2025-08-02	R0CKSTAR	llama-bench: rename DB table name from test to llama_be...	commit \| commitdiff \| tree
2025-08-02	Jeff Bolz	vulkan: Support ne[3]>1 in noncontig matrix-vector...	commit \| commitdiff \| tree
2025-08-02	Douglas Hanley	model : support Qwen3-Embedding (#15023)	commit \| commitdiff \| tree
2025-08-02	Johannes Gäßler	server: enable token array inputs for OAI API (#15001)	commit \| commitdiff \| tree
2025-08-02	Jeff Bolz	vulkan: optimizations for direct convolution (#14933)	commit \| commitdiff \| tree
2025-08-01	Johannes Gäßler	CUDA: fix MMQ nwarps for AMD with warp_size==32 (#15014)	commit \| commitdiff \| tree
2025-08-01	l-austenfeld	vendor : update vendored copy of google/minja (#15011)	commit \| commitdiff \| tree
2025-08-01	stevenkuang	model : add hunyuan dense (#14878)	commit \| commitdiff \| tree
2025-08-01	lhez	opencl: add f16 for `add`, `sub`, `mul`, `div` (#14984)	commit \| commitdiff \| tree
2025-08-01	Srihari-mcw	ggml : Q2k interleaving implementation - x86/x64 SIMD...	commit \| commitdiff \| tree
2025-08-01	Georgi Gerganov	graph : fix equal_seq() check (#14986)	commit \| commitdiff \| tree
2025-08-01	diannao	docker : add cann build pipline (#14591)	commit \| commitdiff \| tree
2025-08-01	R0CKSTAR	compare-commits.sh: support both llama-bench and test...	commit \| commitdiff \| tree
2025-07-31	Ed Addario	quantize : skip tensor override when in fallback mode...	commit \| commitdiff \| tree
2025-07-31	Diego Devesa	llama : add simple option to enable CPU for MoE weights...	commit \| commitdiff \| tree
2025-07-31	Aman Gupta	Fix params bug in diffusion example (#14993)	commit \| commitdiff \| tree
2025-07-31	Diego Devesa	llama : allow other bufts when overriding to CPU, add...	commit \| commitdiff \| tree
2025-07-31	Ruben Ortlam	Vulkan: Fix minor debug mode issues (#14899)	commit \| commitdiff \| tree
2025-07-31	tc-mb	mtmd : support MiniCPM-V 4.0 (#14983)	commit \| commitdiff \| tree
2025-07-31	Csaba Kecskemeti	MODEL_TENSOR.SSM_DT_NORM has defined twice (#14991)	commit \| commitdiff \| tree
2025-07-31	g2mt	server : implement universal assisted decoding (#12635)	commit \| commitdiff \| tree
2025-07-31	Dongliang Wei	llama : merge build_moe_ffn_from_probs function into...	commit \| commitdiff \| tree
2025-07-31	Lukas Straub	server : add openai-style logit_bias support (#14946)	commit \| commitdiff \| tree
2025-07-31	Aman Gupta	Add LLaDA 8b Diffusion model (#14771)	commit \| commitdiff \| tree
2025-07-31	hipudding	CANN: Improve loading efficiency after converting weigh...	commit \| commitdiff \| tree
2025-07-31	compilade	graph : reduce splits for recurrent and hybrid models...	commit \| commitdiff \| tree
2025-07-30	lhez	opencl: add `mul_mat_f32_f32_l4_lm` and `mul_mat_f16_f3...	commit \| commitdiff \| tree
2025-07-30	Ed Addario	quantize : fix using combined imatrix GGUFs (multiple...	commit \| commitdiff \| tree
2025-07-30	Daniel Bevenius	server : add support for `embd_normalize` parameter...	commit \| commitdiff \| tree
2025-07-30	uvos	HIP: enable mfma mmq on gfx908 and gfx90a for select...	commit \| commitdiff \| tree
2025-07-30	Georgi Gerganov	sync : ggml	commit \| commitdiff \| tree
next

Packaging of ggml-org/llama.cpp

RSS Atom