]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2026-02-24 Max Krasnyanskyhexagon refactor all Ops to use local context struct...
2026-02-23 Aleksander... feat: Add code blocks full height setting to parameter...
2026-02-23 Adrien Gallouëtvendor : update cpp-httplib to 0.34.0 (#19830)
2026-02-23 Daniel Beveniustests : fix typos in comments in test-backend-sampler...
2026-02-23 Aleksander... webui: Add setting to have full height Code Blocks...
2026-02-23 Daniel Beveniusmodel-conversion : merge inspect-org-model.py with...
2026-02-23 Alberto Cabrera... ggml-cpu: arm64: q5_K repack gemm and gemv (and generic...
2026-02-23 Daniel Beveniusllama : remove write/read of output ids/logits/embeddin...
2026-02-22 Sigbjørn Skjæretcli : provide model with text filename (#19783)
2026-02-22 Xuan-Son Nguyenjinja: correct stats for tojson and string filters...
2026-02-22 Aldehir Rojascommon : fix improper trimming in XML parser on complet...
2026-02-22 Kilian KrampfFix wrong cli-argument in documentation (#19804)
2026-02-22 HelloKSmodel : add Kanana-2 model support (#19803)
2026-02-22 Sigbjørn Skjæretci : fix rocm archive name [no ci] (#19808)
2026-02-22 Aldehir Rojasserver : merge contiguous Responses input items into...
2026-02-22 Sigbjørn Skjæretci : fix rocm release path [no ci] (#19784)
2026-02-21 Mario LimoncielloUpdate ROCm docker container to 7.2 release (#19418)
2026-02-21 Mario LimoncielloAdd a build target to generate ROCm artifacts using...
2026-02-21 Adrien Gallouëtvendor : update cpp-httplib to 0.33.1 (#19778)
2026-02-21 Gaurav GargImprove CUDA graph capture (#19754)
2026-02-21 crsawyerfix: UI single model selection in router mode (#19767)
2026-02-21 Mengsheng Wuhexagon : fix build release (#19444) (#19587)
2026-02-20 Aldehir Rojascommon : merge qwen3-coder and nemotron nano 3 parsers...
2026-02-20 Taimur Ahmadggml-cpu: add RVV vec dot kernels for quantization...
2026-02-20 ddh0quantize : add --dry-run option (#19526)
2026-02-20 Jeff Bolztest: mul_mat tests with huge batch size (#19519)
2026-02-19 crsawyerWebUI hide models in router mode (#19374)
2026-02-19 Jesse Posnercommon : fix Step-3.5-Flash format detection and thinki...
2026-02-19 abhijitb11common : fix gpt-oss Jinja error when assistant message...
2026-02-19 Masashi Yoshimuraggml-webgpu: Add unary op (SQR, SQRT, SIN, COS) support...
2026-02-19 megeminimodel: Add PaddleOCR-VL model support (#18825)
2026-02-19 Ruben Ortlamvulkan: fix MMQ shader push constants and multi-dispatc...
2026-02-19 Georgi Gerganovmodels : fix qwen3.5 beta/gate shapes (#19730)
2026-02-19 Saba Fallahmtmd: build_attn modified, flash_attn on/off via ctx_pa...
2026-02-19 3 a l imodel : add JAIS-2 architecture support (#19488)
2026-02-19 Johannes GäßlerCUDA: fix kernel selection logic for tile FA (#19686)
2026-02-19 Tarek Dakhranmtmd : chat : Fix extra \n between text and media marke...
2026-02-19 Aleksander... webui: Fix Attachments not being included in completion...
2026-02-19 Tarek Dakhranmodel : add tokenizer from LFM2.5-Audio-1.5B (#19687)
2026-02-19 Daniel Beveniusllama : use output_resolve_row() in get_logits_ith...
2026-02-19 Ryan Mangenomodel : full modern bert support (#18330)
2026-02-19 shalinib-ibmllamafile: powerpc: add FP16 MMA path for Q4/Q8 matmul...
2026-02-19 Georgi Gerganovmodels : dedup qwen35 graphs (#19660)
2026-02-19 ymckimodels : dedup Kimi Linear delta net implementation...
2026-02-18 Piotr Wilkin... Add Jinja support for "indent" string filter (#19529)
2026-02-18 Reese Levineggml webgpu: Fix bug in dispatching large matrix-vector...
2026-02-18 matteoserver: save generated text for the /slots endpoint...
2026-02-18 Xuan-Son Nguyenmodel: support GLM-OCR (#19677)
2026-02-18 Maciej Lisowskidocs: Fix broken links for preparing models in Backends...
2026-02-18 Reese Levineggml webgpu: shader library organization (#19530)
2026-02-18 Aleksander... Pre-MCP UI and architecture cleanup (#19689)
2026-02-18 Jeff Bolzvulkan: split mul_mat into multiple dispatches to avoid...
2026-02-18 Adrien Gallouëtcommon : make small string helpers as inline functions...
2026-02-17 shaofeiqiopencl: refactor expm1 and softplus (#19404)
2026-02-17 shaofeiqiopencl: optimize mean and sum_row kernels (#19614)
2026-02-17 Daniel Beveniusmodel-conversion : add option to print tensor values...
2026-02-17 Aleksander... Pre-MCP UI and architecture cleanup (#19685)
2026-02-17 Talha Can Havadarggml: ggml-cpu: force-no-lto-for-cpu-feats (#19609)
2026-02-17 Georgi Gerganovcuda : enable CUDA graphs for MMID 1 <= BS <= 4 (#19645)
2026-02-17 Daniel Beveniusmodel-conversion : make printing of config values optio...
2026-02-17 Sigbjørn Skjæretci : bump komac version (#19682)
2026-02-17 Adrien Gallouëtbuild : link ws2_32 as PUBLIC on Windows (#19666)
2026-02-17 Adrien Gallouëtbuild : cleanup library linking logic (#19665)
2026-02-16 DAN™convert : add JoyAI-LLM-Flash (#19651)
2026-02-16 AesSedaiperplexity: add proper batching (#19661)
2026-02-16 Ivan Chikishcommon : inline functions (#18639)
2026-02-16 Juddggml : make `ggml_is_view` as API (#19539)
2026-02-16 Saurabh Dashmodel: Add support for Tiny Aya Models (#19611)
2026-02-16 Adrien Gallouëtbuild : rework llama_option_depr to handle LLAMA_CURL...
2026-02-16 Mario LimoncielloAdjust workaround for ROCWMMA_FATTN/GFX9 to only newer...
2026-02-16 Georgi Gerganovmodels : deduplicate delta-net graphs for Qwen family...
2026-02-16 Georgi Gerganovgraph : fix KQ mask, lora, cvec reuse checks (#19644)
2026-02-16 abhijain1204fujitsuggml: aarch64: Implement SVE in Gemm q4_k 8x8 q8_k...
2026-02-15 Georgi Gerganovsync : ggml upstream/0.0.8067
2026-02-15 Georgi Gerganovggml : bump version to 0.9.7 (ggml/1425)
2026-02-15 Georgi Gerganovggml : bump version to 0.9.6 (ggml/1423)
2026-02-15 David Friehscuda: optimize iq2xxs/iq2xs/iq3xxs dequantization ...
2026-02-15 Aaron Teodocs: update s390x build docs (#19643)
2026-02-15 Adrien Gallouëtbuild : remove LLAMA_HTTPLIB option (#19623)
2026-02-15 Daniel Beveniuscmake : check if KleidiAI API has been fetched (#19640)
2026-02-15 Georgi Gerganovcontext : fix output reorder with backend sampling...
2026-02-15 Georgi Gerganovggml : avoid UB in gemm ukernel (#19642)
2026-02-15 Aaron Teoggml-cpu: optimize ggml_vec_dot_bf16 for s390x (#19399)
2026-02-15 Aman Guptaggml-cpu: FA add GEMM microkernel (#19422)
2026-02-15 SamareshSinghcmake : fix KleidiAI install target failure with EXCLUD...
2026-02-14 Sigbjørn Skjæretconvert : ensure all models handle new experts count...
2026-02-14 Anav Prasadmtmd : Add Nemotron Nano 12B v2 VL support (#19547)
2026-02-14 Georgi Gerganovmodels : optimize qwen3next graph (#19375)
2026-02-14 Adrien Gallouëtggml : fix GGML_DEBUG with OpenMP (#19599)
2026-02-14 iMilNetBSD build support (#19589)
2026-02-14 Aleksander... webui: Architecture and UI improvements (#19596)
2026-02-14 agent-enemy-2llama : update LoRA API. + fix excessive graph reserves...
2026-02-14 Georgemmap: Fix Windows handle lifetime (#19598)
2026-02-14 Georgi Gerganovmetal : fix ACC op (#19427)
2026-02-14 Adrien Gallouëtscripts : use official split.py for cpp-httplib (#19588)
2026-02-14 Sigbjørn Skjæretconvert : store ffn_gate_inp_shexp as F32 (#19606)
2026-02-14 Adrien Gallouëtbuild : fix libtool call in build-xcframework.sh (...
2026-02-14 Jeff Bolzvulkan: support L2_NORM with contiguous rows (#19604)
2026-02-14 Jeff Bolzvulkan: support GGML_OP_SET (#19584)
2026-02-14 Sophonvulkan: Add vendor id for Qualcomm drivers (#19569)
next