]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-06-11 Georgi Gerganovkv-cache : relax SWA masking condition (#14119)
2025-06-11 Taylorserver : pass default --keep argument (#14120)
2025-06-11 Georgi Gerganovkv-cache : add LLAMA_KV_CACHE_DEBUG environment variabl...
2025-06-11 Jeff Bolzvulkan: Track descriptor pools/sets per-context (#14109)
2025-06-10 lhezopencl: add `mul_mv_id_q4_0_f32_8x_flat` (#14003)
2025-06-10 compiladekv-cache : avoid modifying recurrent cells when setting...
2025-06-10 Sigbjørn Skjæretconvert : fix duplicate key DeepSeek-R1 conversion...
2025-06-10 Sigbjørn Skjæretllama : support GEGLU for jina-bert-v2 (#14090)
2025-06-10 Jeff Bolzvulkan: force device 0 in CI (#14106)
2025-06-10 Juk ArmstrongFixed spec timings to: accepted/tested instead of accep...
2025-06-10 Georgi Gerganovsync : ggml
2025-06-10 Georgi Gerganovggml : fix weak alias win32 (whisper/0)
2025-06-10 0cc4mVulkan: Don't default to CPU device (like llvmpipe...
2025-06-10 Isaac McFadyenrpc : nicer error messages for RPC server crash (#14076)
2025-06-10 Georgi Gerganovsync : ggml
2025-06-10 Kai PastorAdd in-build ggml::ggml ALIAS library (ggml/1260)
2025-06-09 Georgi Gerganovmetal : use less stack memory in FA kernel (#14088)
2025-06-09 Georgi Gerganovkv-cache : fix shift and defrag logic (#14081)
2025-06-09 Diego Devesallama : allow building all tests on windows when not...
2025-06-09 xctanggml-cpu : split arch-specific implementations (#13892)
2025-06-09 Diego Devesacuda : fix device sync on buffer clear (#14033)
2025-06-09 Georgi Gerganovgraph : fix geglu (#14077)
2025-06-09 Xinpeng DouCANN: Simplify the environment variable setting(#13104)
2025-06-09 R0CKSTARwebui: fix sidebar being covered by main content (...
2025-06-09 Georgi Gerganovserver : fix LRU check (#14079)
2025-06-09 Nicolò Scipionesycl: Add reorder to Q6_K mmvq implementation (#13885)
2025-06-09 Đinh Trọng Huyadd geglu activation function (#14074)
2025-06-09 Yuanhao JiCANN: Enable labeler for Ascend NPU (#13914)
2025-06-08 Diego Devesacuda : fix buffer type check with integrated GPUs ...
2025-06-07 吴小白ci: add LoongArch cross-compile build (#13944)
2025-06-07 Akarshan BiswasSYCL: Implement few same quantized type copy kernels...
2025-06-07 Sigbjørn Skjæretllama : fix llama_model_chat_template with template...
2025-06-06 Georgi Gerganovllama : deprecate llama_kv_self_ API (#14030)
2025-06-06 Georgi Gerganovcontext : fix SWA-related warning for multiple sequence...
2025-06-06 Sigbjørn Skjæretllama : support multiple classifier outputs and labels...
2025-06-05 Sigbjørn Skjæretgguf-py : add add_classifier_output_labels method to...
2025-06-05 Masato Nakasakavulkan: Enable VK_KHR_cooperative_matrix extension...
2025-06-05 pockers21ci: fix CUDA build failure on autodl cloud machines...
2025-06-05 Georgi Gerganovmemory : migrate from llama_kv_cache to more generic...
2025-06-05 Diego Devesallama : allow using mmap without PrefetchVirtualMemory...
2025-06-05 Olexandr88readme : add badge (#13938)
2025-06-05 Sigbjørn Skjæretvocab : warn about missing mask token (#14022)
2025-06-05 Georgi Gerganovcontext : fix pos_min initialization upon error decode...
2025-06-05 Jeff Bolzvulkan: automatically deduce size of push constants...
2025-06-04 Ervin Áron... ggml-vulkan: adds support for op CONV_TRANSPOSE_1D...
2025-06-04 Georgi Gerganovkv-cache : refactor the update/defrag mechanism (#13988)
2025-06-04 Diego Devesaci : remove cuda 11.7 releases, switch runner to window...
2025-06-04 Diego Devesareleases : use dl backend for linux release, remove...
2025-06-04 Xuan-Son Nguyenllama-graph : use ggml_repeat_4d (#13998)
2025-06-04 Johannes GäßlerCUDA: fix FTZ in FA for Gemma 3 (#13991)
2025-06-04 Georgi Gerganovkv-cache : fix unified::seq_rm to work with seq_id...
2025-06-03 Jeff Bolzvulkan: fix warnings in perf logger querypool code...
2025-06-03 Xuan-Son Nguyendocs : add "Quick start" section for new users (#13862)
2025-06-02 lhezopencl: add `backend_synchronize` (#13939)
2025-06-02 rmatifOpenCL: Add concat, tsembd, upscale, tanh, pad and...
2025-06-02 Georgi Gerganovserver : disable speculative decoding for SWA models...
2025-06-02 Georgi Gerganovmetal : use F32 accumulators in FA kernels (#13975)
2025-06-02 Georgi Gerganovgemma : more consistent attention scaling for v2 and...
2025-06-02 Olivier Chafik`server`: update deepseek reasoning format (pass reason...
2025-06-02 Xuan-Son Nguyenmtmd : fix memory leak in mtmd_helper_eval_chunk_single...
2025-06-02 shalinib-ibmcmake : Handle mixed-case 'Power' strings in POWER...
2025-06-02 Atharva Dubeysycl: quantize and reorder the input to q8_1 when reord...
2025-06-01 Johannes Gäßlergguf: fix failure on version == 0 (#13956)
2025-06-01 Sigbjørn Skjæretconvert : fix nomic-bert-moe mask token (#13757)
2025-06-01 Sigbjørn Skjæretconvert : fix vocab padding code for bert models (...
2025-06-01 Aaron Teoggml: check if non-native endian model is being loaded...
2025-06-01 Georgi Gerganovsync : ggml
2025-06-01 Kai Pastorvulkan : Remove unexpected ; (ggml/1253)
2025-06-01 Kai Pastorcmake : Fix broken CMake error messages (ggml/1252)
2025-06-01 Radoslav Gerganovggml : remove ggml_graph_import and ggml_graph_export...
2025-06-01 Georgi Gerganovsync : whisper.cpp (ggml/1250)
2025-06-01 Radoslav Gerganovggml : install dynamic backends (ggml/1240)
2025-06-01 Daniel Tangggml : Print backtrace on uncaught C++ exceptions ...
2025-06-01 ddh0readme : update bindings (#13950)
2025-06-01 Georgi Gerganovparallel : fix n_junk == 0 (#13952)
2025-06-01 Georgi Gerganovkv-cache : split implementation in separate sources...
2025-05-31 Max Krasnyanskythreading: support for GGML_SCHED_PRIO_LOW, update...
2025-05-31 Jiří Podivíndocs : Note about necessity of having libcurl installed...
2025-05-31 Olivier Chafikserver: allow unclosed thinking tags (#13931)
2025-05-31 Georgi Gerganovllama : deprecate explicit kv_self defrag/update calls...
2025-05-31 Georgi Gerganovllama : use n_swa + n_ubatch cells for SWA cache (...
2025-05-31 igardevwebui : Replace alert and confirm with custom modals...
2025-05-31 Georgi Gerganovllama : auto-batch preparation (#13845)
2025-05-31 Xuan-Son Nguyenmtmd : drop `_shared` from `libmtmd` name, merge helper...
2025-05-31 Georgi Gerganovkv-cache : refactor + add llama_memory_state_i (#13746)
2025-05-31 Shawn yangCUDA: add a prop in ggml_cuda_device_infor for distingu...
2025-05-30 Johannes GäßlerCUDA: fix typo in FlashAttention code (#13926)
2025-05-30 Diego Devesasched : avoid changing cur_copy when a graph is already...
2025-05-30 Georgi Gerganovparallel : increase the variability of the prompt lengt...
2025-05-30 Diego Devesacuda : prevent using split buffers with 3d/4d matrices...
2025-05-30 Akarshan BiswasSYCL: Add mrope kernel (#13755)
2025-05-30 Georgi Gerganovsync : vendor (#13901)
2025-05-30 Sigbjørn Skjæretconvert : fix rwkv bos/eos token (#13844)
2025-05-30 Xuan-Son Nguyenconvert : allow partial update to the chkhsh pre-tokeni...
2025-05-30 Đinh Trọng Huyllama : add support for DistilBert (#13907)
2025-05-30 zhangkaihuollama : use llm_build_granite for minicpm (#13911)
2025-05-29 Christian Kastnercmake: Guard GGML_CPU_ALL_VARIANTS by architecture...
2025-05-29 Sigbjørn Skjæretllama : add support for jina-reranker-v2 (#13900)
2025-05-29 Sigbjørn Skjæretgguf-py : add support for sub_type (in arrays) in GGUFW...
2025-05-29 Yibo Caiarm64: optimize q4_k_q8_k kernel with i8mm (#13886)
next