]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
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)
2026-02-14 Max Krasnyanskyhexagon: further optimizations and refactoring for...
2026-02-13 Mengsheng Wugithub : add missing backends to issue templates (...
2026-02-13 Jeff Bolzvulkan: restore -inf check in FA shaders (#19582)
2026-02-13 Adrien Gallouëtcommon : update download code (#19573)
2026-02-13 Xuan-Son Nguyenmodel: support GLM MoE DSA arch (NOTE: indexer is not...
2026-02-13 Alberto Cabrera... Fix wrong memcpy length for block_interleave == 4 ...
2026-02-13 ymckifix vulkan ggml_acc only works in 3d but not 4d (#19426)
2026-02-13 Sigbjørn Skjæretsupport --verbose-prompt (#19576)
2026-02-13 Aman GuptaCUDA: loop over ne2*ne3 in case it overflows (#19538)
2026-02-13 Aleksander... webui: UI and routing fixes (#19586)
2026-02-13 Oliver SimonsCUDA: Do not mutate cgraph for fused ADDs (#19566)
2026-02-13 Pavan Shindedocs : fix broken link and typo (#19560)
2026-02-13 ymckimodel : Kimi Linear fix conv state update (#19531)
2026-02-13 Adrien Gallouëtllama : remove deprecated codecvt (#19565)
2026-02-13 Adrien Gallouëtvendor : update BoringSSL to 0.20260211.0 (#19562)
2026-02-13 Georgi Gerganovmemory : fix kv cache size for hybrid models (#19559)
2026-02-13 Georgi Gerganovmetal : improve concurrency (#19555)
2026-02-13 Georgi Gerganovmetal : support GGML_OP_SET (#19548)
2026-02-12 Shupei Fanhexagon: fix typo in vtcm_needs_release (#19545)
2026-02-12 lhezopencl: add basic support for q4_1 (#19534)
2026-02-12 Georgi Gerganovargs : add -kvu to llama-parallel (#19577)
2026-02-12 Aleksander... webui: Add switcher to Chat Message UI to show raw...
2026-02-12 Adrien Gallouëtvendor : update cpp-httplib (#19537)
2026-02-12 Christian Schmitzllama : update outdated comment in llama.h (#19428)
2026-02-12 Aleksander... (webui) FEATURE: Enable adding or injecting System...
2026-02-12 Daniel Beveniusscripts : add support for forks in pr2wt.sh (#19540)
2026-02-12 Aleksander... (webui) REFACTOR: UI primitives and polish (#19551)
next