git.djapps.eu Git - pkg/ggml/sources/llama.cpp/history

]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/history

overview / pkg / ggml / sources / llama.cpp / history

2026-03-06	Aleksander Grygier	webui: Agentic Loop + MCP Client with support for Tools...	\| commitdiff
2026-03-06	Johannes Gäßler	ggml-cpu: fix data race for debug asserts (#20148)	\| commitdiff
2026-03-06	Georgi Gerganov	kv-cache : fix M-RoPE checkpoints (#20132)	\| commitdiff
2026-03-06	Roj234	cli : Don't clear system prompt when using '/clear...	\| commitdiff
2026-03-06	lhez	opencl: add neg, exp and diag (#20127)	\| commitdiff
2026-03-06	YardenTal44	hexagon: add fp16 support for binary ops: add,sub,mul...	\| commitdiff
2026-03-05	ymcki	models : kda chunk size = 16 (#19827)	\| commitdiff
2026-03-05	Andreas Kieslinger	CUDA: Improve performance via less synchronizations...	\| commitdiff
2026-03-05	Eric Zhang	model : update Qwen3.5 model type detection (#20126)	\| commitdiff
2026-03-05	Sigbjørn Skjæret	cli : add command and file auto-completion (#19985)	\| commitdiff
2026-03-05	Sigbjørn Skjæret	convert : register Qwen 3.5 ForCausalLM for text only...	\| commitdiff
2026-03-05	Aleksander Grygier	webui: Improvements for Models Selector UI (#20066)	\| commitdiff
2026-03-05	Marcel Petrick	chore : correct typos [no ci] (#20041)	\| commitdiff
2026-03-05	Max Krasnyansky	hexagon: Flash Attention optimizations (dma, mpyacc...	\| commitdiff
2026-03-05	lhez	opencl: add `SET`, support i32 for `CPY`, minor refacto...	\| commitdiff
2026-03-04	Todor Boinovski	hexagon: add llama-completion runner script (#20095)	\| commitdiff
2026-03-04	Nikhil Jain	[WebGPU] Fix wait logic for inflight jobs (#20096)	\| commitdiff
2026-03-04	Masashi Yoshimura	Add concat op to webgpu. (#20068)	\| commitdiff
2026-03-04	Sigbjørn Skjæret	tools : add missing clocale include in mtmd-cli [no...	\| commitdiff
2026-03-04	Johannes Gäßler	ggml: fix ggml_is_contiguous_n for ne == 1 (#20092)	\| commitdiff
2026-03-04	Adrien Gallouët	ggml : use a simple std::thread in AMX without OpenMP...	\| commitdiff
2026-03-04	ddh0	impl : use 6 digits for tensor dims (#20094)	\| commitdiff
2026-03-04	SamareshSingh	Fix locale-dependent float printing in GGUF metadata...	\| commitdiff
2026-03-04	standby24x7	completion : Fix a typo in warning message (#20082)	\| commitdiff
2026-03-03	Mickael Desgranges	docs: Fix intel documentation link (#20040)	\| commitdiff
2026-03-03	Charles Xu	kleidiai : add sme fp16 compute path for q4_0 gemm...	\| commitdiff
2026-03-03	shaofeiqi	opencl: add optimized q4_1 mm kernel for adreno (#19840)	\| commitdiff
2026-03-03	Abhijit Ramesh	ggml webgpu: fix workgroup dispatch limit for large...	\| commitdiff
2026-03-02	Nikhil Jain	ggml webgpu: Clean up per-thread parameter buffer pool...	\| commitdiff
2026-03-02	Masashi Yoshimura	ggml-webgpu: Support non-contiguous `src0` and overlapp...	\| commitdiff
2026-03-02	Ruben Ortlam	vulkan: tune MMVQ for Intel Windows (#19988)	\| commitdiff
2026-03-02	Adrien Gallouët	scripts : improve get-wikitext-2.sh (#19952)	\| commitdiff
2026-03-02	Aaron Teo	ggml-cpu: optimise s390x multiply extend instructions...	\| commitdiff
2026-03-01	Ruben Ortlam	vulkan: improve partial offloading performance on AMD...	\| commitdiff
2026-03-01	oobabooga	cuda: cap grid.y at 65535 in non-contiguous dequantize...	\| commitdiff
2026-02-28	Dmitry Atamanov	vendors : update miniaudio library to 0.11.24 (#19914)	\| commitdiff
2026-02-28	Adrien Gallouët	vendor : update cpp-httplib to 0.35.0 (#19969)	\| commitdiff
2026-02-28	Bartowski	tests : model metadata loading from huggingface (#19796)	\| commitdiff
2026-02-27	Jayant Lohia	CUDA: add CDNA3 MFMA support for flash attention MMA...	\| commitdiff
2026-02-27	Roj234	server: Add pragma once to server-context.h (#19944)	\| commitdiff
2026-02-27	Sami Kama	server: Mirroring /v1/responses to /responses to match...	\| commitdiff
2026-02-27	Daniel Bevenius	ci : use ubuntu-latest for gguf-publish workflow (...	\| commitdiff
2026-02-27	Aman Gupta	ggml-cpu: add repack for mxfp4 (#19738)	\| commitdiff
2026-02-27	Daniel Bevenius	gguf-py : dump version to 0.18.0 (#19950) gguf-v0.18.0	\| commitdiff
2026-02-27	Pascal	server : support multiple model aliases via comma-separ...	\| commitdiff
2026-02-27	Jan Patrick Lehr	tests : enable test-chat out of tree build (#19558)	\| commitdiff
2026-02-27	Neo Zhang	replace the magic nunber 768 by max work group size...	\| commitdiff
2026-02-27	Vishal Singh	ggml-zendnn: update code for latest ZenDNN API (#19923)	\| commitdiff
2026-02-26	Adrien Gallouët	ggml : fix AMX and add batched support (#19925)	\| commitdiff
2026-02-26	Ruben Ortlam	vulkan: fix fp16 Flash Attention on Windows AMD RDNA2...	\| commitdiff
2026-02-26	Georgi Gerganov	mtmd : fix padding of n_tokens (#19930)	\| commitdiff
2026-02-26	Georgi Gerganov	server : fix ctx checkpoint restore logic (#19924)	\| commitdiff
2026-02-26	Georgi Gerganov	kv-cache : fix can_shift() check to take into account...	\| commitdiff
2026-02-26	Aman Gupta	llama: Add option to merge gate and exp weights (#19139)	\| commitdiff
2026-02-26	Kevin Pouget	ggml-virtgpu: improve the reliability of the code ...	\| commitdiff
2026-02-26	drrros	server: fix load-on-startup not respected in ini file...	\| commitdiff
2026-02-26	Eric Zhang	jinja : correct default size for string slices (#19913)	\| commitdiff
2026-02-26	Maximilian Werk	model : add Jina Embeddings v5 Nano (partial EuroBERT...	\| commitdiff
2026-02-26	Georgi Gerganov	gguf : avoid too many file size calls (#19919)	\| commitdiff
2026-02-26	yggdrasil75	server : fix typo in server README.md (#19900)	\| commitdiff
2026-02-26	Neo Zhang	support permuted, remove check s0/s10 (#19889)	\| commitdiff
2026-02-25	Jeff Bolz	vulkan: check for memory overlap before doing fusion...	\| commitdiff
2026-02-25	ddh0	common : add more aliases for sampler CLI params (...	\| commitdiff
2026-02-25	Slobodan Josic	ci : update the ROCm/HIP toolchain versions [no ci...	\| commitdiff
2026-02-25	Georgi Gerganov	server : enable multi-modal prompt caching (#19877)	\| commitdiff
2026-02-25	Georgi Gerganov	server : support multi-modal context checkpoints (...	\| commitdiff
2026-02-25	Xuan-Son Nguyen	scripts: update corpus of compare-logprobs (#19326)	\| commitdiff
2026-02-25	Mario Limonciello	ci : update Windows ROCm build to 26.Q1 [no ci] (#19810)	\| commitdiff
2026-02-25	Aldehir Rojas	gguf : fix ftell/fseek for Windows (#19870)	\| commitdiff
2026-02-24	Georgi Gerganov	models : fix graph splits (#19866)	\| commitdiff
2026-02-24	Pascal	server: fix query params lost when proxying requests...	\| commitdiff
2026-02-24	Georgi Gerganov	ggml/gguf : prevent integer overflows (#19856)	\| commitdiff
2026-02-24	Tarek Dakhran	model : update label for LFM2-24B-A2B (#19848)	\| commitdiff
2026-02-24	Radoslav Gerganov	server : support max_completion_tokens request property...	\| commitdiff
2026-02-24	Ruben Ortlam	Vulkan Scalar Flash Attention Refactor (#19625)	\| commitdiff
2026-02-24	Jeff Bolz	vulkan: fix coopmat1 without bf16 support (#19793)	\| commitdiff
2026-02-24	Jeff Bolz	vulkan: fix data race in mul_mat_id shader (#19790)	\| commitdiff
2026-02-24	Max Krasnyansky	hexagon refactor all Ops to use local context struct...	\| commitdiff
2026-02-23	Aleksander Grygier	feat: Add code blocks full height setting to parameter...	\| commitdiff
2026-02-23	Adrien Gallouët	vendor : update cpp-httplib to 0.34.0 (#19830)	\| commitdiff
2026-02-23	Daniel Bevenius	tests : fix typos in comments in test-backend-sampler...	\| commitdiff
2026-02-23	Aleksander Grygier	webui: Add setting to have full height Code Blocks...	\| commitdiff
2026-02-23	Daniel Bevenius	model-conversion : merge inspect-org-model.py with...	\| commitdiff
2026-02-23	Alberto Cabrera...	ggml-cpu: arm64: q5_K repack gemm and gemv (and generic...	\| commitdiff
2026-02-23	Daniel Bevenius	llama : remove write/read of output ids/logits/embeddin...	\| commitdiff
2026-02-22	Sigbjørn Skjæret	cli : provide model with text filename (#19783)	\| commitdiff
2026-02-22	Xuan-Son Nguyen	jinja: correct stats for tojson and string filters...	\| commitdiff
2026-02-22	Aldehir Rojas	common : fix improper trimming in XML parser on complet...	\| commitdiff
2026-02-22	Kilian Krampf	Fix wrong cli-argument in documentation (#19804)	\| commitdiff
2026-02-22	HelloKS	model : add Kanana-2 model support (#19803)	\| commitdiff
2026-02-22	Sigbjørn Skjæret	ci : fix rocm archive name [no ci] (#19808)	\| commitdiff
2026-02-22	Aldehir Rojas	server : merge contiguous Responses input items into...	\| commitdiff
2026-02-22	Sigbjørn Skjæret	ci : fix rocm release path [no ci] (#19784)	\| commitdiff
2026-02-21	Mario Limonciello	Update ROCm docker container to 7.2 release (#19418)	\| commitdiff
2026-02-21	Mario Limonciello	Add a build target to generate ROCm artifacts using...	\| commitdiff
2026-02-21	Adrien Gallouët	vendor : update cpp-httplib to 0.33.1 (#19778)	\| commitdiff
2026-02-21	Gaurav Garg	Improve CUDA graph capture (#19754)	\| commitdiff
2026-02-21	crsawyer	fix: UI single model selection in router mode (#19767)	\| commitdiff
2026-02-21	Mengsheng Wu	hexagon : fix build release (#19444) (#19587)	\| commitdiff
2026-02-20	Aldehir Rojas	common : merge qwen3-coder and nemotron nano 3 parsers...	\| commitdiff
next

Packaging of ggml-org/llama.cpp

RSS Atom