]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/shortlog
pkg/ggml/sources/llama.cpp
2025-07-31 hipuddingCANN: Improve loading efficiency after converting weigh...
2025-07-31 compiladegraph : reduce splits for recurrent and hybrid models...
2025-07-30 lhezopencl: add `mul_mat_f32_f32_l4_lm` and `mul_mat_f16_f3...
2025-07-30 Ed Addarioquantize : fix using combined imatrix GGUFs (multiple...
2025-07-30 Daniel Beveniusserver : add support for `embd_normalize` parameter...
2025-07-30 uvosHIP: enable mfma mmq on gfx908 and gfx90a for select...
2025-07-30 Georgi Gerganovsync : ggml
2025-07-30 Kai Pastorcmake : Fix BLAS link interface (ggml/1316)
2025-07-30 Kai Pastorvulkan : fix 32-bit builds (ggml/1313)
2025-07-30 Johannes GäßlerCUDA: skip masked KV slices for all FA kernels (#14924)
2025-07-30 Georgi Gerganovtests : update for LLAMA_SET_ROWS=1 (#14961)
2025-07-30 Georgi Gerganovgraph : fix stack-use-after-return (#14960)
2025-07-30 Douglas Hanleyembeddings: fix extraction of CLS pooling results ...
2025-07-30 Xinpeng DouCANN: update ops docs (#14935)
2025-07-29 uvosHIP: remove the use of __HIP_PLATFORM_AMD__, explicitly...
2025-07-29 uvosHIP: add GGML_HIP_MMQ_MFMA option to allow disableing...
2025-07-29 uvosHIP: Ignore unsupported unroll transformation in fattn...
2025-07-29 kallewoofcommon : avoid logging partial messages (which can...
2025-07-29 hipuddingCANN: Add ggml_set_rows (#14943)
2025-07-29 Sigbjørn Skjæretcuda : add softcap fusion (#14907)
2025-07-29 Johannes Gäßlerserver-bench: make seed choice configurable (#14929)
2025-07-29 Aman GuptaCUDA: add roll (#14919)
2025-07-28 lhezopencl : add ops docs (#14910)
2025-07-28 Leonard Mosescutest-backend-ops : extend test case filtering (#14865)
2025-07-28 Radoslav Gerganovllama-bench : use local GPUs along with RPC servers...
2025-07-28 xctanggml-cpu : deduplicate scalar implementations (#14897)
2025-07-28 Akarshan BiswasSYCL: Add set_rows support for quantized types (#14883)
2025-07-28 Xuan-Son Nguyenmtmd : add support for Voxtral (#14862)
2025-07-28 Johannes GäßlerCUDA: fix pointer incrementation in FA (#14916)
2025-07-28 Dongliang Weimodel : add support for SmallThinker series (#14898)
2025-07-28 Alberto Cabrera... sycl: refactor quantization to q8_1 (#14815)
2025-07-28 Georgi Gerganovops : update BLAS (#14914)
2025-07-28 Georgi Gerganovops : update Metal (#14912)
2025-07-28 Georgi Gerganovsync : ggml
2025-07-28 Kai Pastorcmake : Indent ggml-config.cmake (ggml/1310)
2025-07-27 Ed Addarioquantize : update README.md (#14905)
2025-07-27 Ruben Ortlamvulkan: add ops docs (#14900)
2025-07-27 Akarshan BiswasSYCL: add ops doc (#14901)
2025-07-27 Daniel Beveniusllama : clarify comment about pp and tg graphs [no...
2025-07-27 Erik Scholzvulkan : add fp16 support for the conv_2d kernel (...
2025-07-27 Jeff Bolzvulkan: skip empty set_rows to avoid invalid API usage...
2025-07-27 Gabriel Larsonmodel : make rope_yarn_log_mul optional for deepseek2...
2025-07-27 Shunta Saitollama : fix kq_scale for the attention layers of PLaMo2...
2025-07-27 Aman GuptaDocs: add instructions for adding backends (#14889)
2025-07-26 deepsekHIP: Enable Matrix cores for MMQ Kernels, Enable stream...
2025-07-26 hipuddingCANN: Implement GLU ops (#14884)
2025-07-26 R0CKSTARmusa: fix build warnings (unused variable) (#14869)
2025-07-25 Aaron Teoggml-cpu : disable GGML_NNPA by default due to instabil...
2025-07-25 Gabe Goodhartmetal: SSM_SCAN performance (#14743)
2025-07-25 lhezopencl: add fused `rms_norm_mul` (#14841)
2025-07-25 wooksongdocs : update HOWTO‑add‑model.md for ModelBase and...
2025-07-25 Oliver Simonsggml : remove invalid portPos specifiers from dot files...
2025-07-25 Georgi Gerganovcontext : restore preemptive sched reset when LLAMA_SET...
2025-07-25 kiwimtmd : fix 32-bit narrowing issue in export-lora and...
2025-07-25 Chris Rohlfrpc : check for null buffers in get/set/copy tensor...
2025-07-25 Diego Devesasched : fix multiple evaluations of the same graph...
2025-07-24 R0CKSTARmusa: upgrade musa sdk to rc4.2.0 (#14498)
2025-07-24 Georgi Gerganovsync : ggml
2025-07-24 Kai Pastorcmake : fix usage issues (ggml/1257)
2025-07-24 Daniel Beveniusggml-cpu : remove stdlib include from repack.cpp (ggml...
2025-07-24 Georgi Gerganovcontext : perform output reorder lazily upon access...
2025-07-24 Xuan-Son Nguyenchat : fix kimi-k2 chat template (#14852)
2025-07-24 Alberto Cabrera... sycl: fixed semantics of block offset calculation ...
2025-07-24 yummyllama : fix MiniCPM inference after Granite Four change...
2025-07-24 Pouyadocs: add libcurl-dev install hint for Linux distros...
2025-07-24 Georgi Gerganovmetal : fix fusion across different encoders (#14849)
2025-07-24 Donghyeon Jeongsycl: fix undefined variable in work group size check...
2025-07-23 jacekpoplawskiconvert : text-only support for GLM-4.1V-9B-Thinking...
2025-07-23 Johannes GäßlerCUDA: fix overflow in FA, tune performance (#14840)
2025-07-23 Johannes GäßlerCUDA: fix compilation with GGML_CUDA_F16 (#14837)
2025-07-23 Sigbjørn Skjæretci : correct label refactor->refactoring (#14832)
2025-07-23 Johannes GäßlerCUDA: fix quantized KV cache + multiple sequences ...
2025-07-23 Georgi Gerganovtests : add non-cont K,V FA tests
2025-07-23 l3utterflymemory : handle saving/loading null layers in recurrent...
2025-07-23 lixing-starggml: fix loongarch quantize_row_q8_1 error (#14827)
2025-07-23 chen fanCANN: weight format to NZ for Ascend310P3 (#14407)
2025-07-23 Aman GuptaCUDA: add fused rms norm (#14800)
2025-07-22 Csaba Kecskemetiggml : model card yaml tab->2xspace (#14819)
2025-07-22 Jeff Bolzvulkan: fix rms_norm_mul to handle broadcasting dim0...
2025-07-22 Molly Sophiallama : add model type detection for rwkv7 7B&14B ...
2025-07-22 Ed Addarioimatrix: add option to display importance score statist...
2025-07-22 stduhpfMtmd: add a way to select device for vision encoder...
2025-07-22 Sigbjørn Skjæretcuda : implement bf16 cpy ops and enable bf16 cont...
2025-07-22 lhezopencl: remove unreachable `return` (#14806)
2025-07-22 Molly Sophiaserver : allow setting `--reverse-prompt` arg (#14799)
2025-07-21 R0CKSTARcuda: remove linking to cublasLt (#14790)
2025-07-21 Sigbjørn Skjæretopencl: fix `im2col` when `KW!=KH` (#14803)
2025-07-21 rmatifopencl: add conv2d kernel (#14403)
2025-07-21 Romain Biessysycl: Fix im2col (#14797)
2025-07-21 Charles Xukleidiai: add support for get_rows (#14676)
2025-07-21 Radoslav Gerganovdocs : fix backends table in README.md (#14796)
2025-07-21 Jeff Bolzvulkan/cuda: Fix im2col when KW!=KH (#14789)
2025-07-21 Molly Sophiallama : fix `--reverse-prompt` crashing issue (#14794)
2025-07-21 IsaacDynamoserver : add parse_special option to /tokenize endpoint...
2025-07-20 Aman Guptadocs : fix link for tools/perplexity in README.md ...
2025-07-20 rspOverflowDocumentation: Further revisions to the Vulkan section...
2025-07-20 Aman GuptaClang-format: local files first + fix BinPacking (...
2025-07-19 0cc4mContrib: add 0cc4m as codeowner for Vulkan backend...
2025-07-19 Ervin Áron... ggml: adds CONV_2D op and direct GEMM Vulkan implementa...
2025-07-19 compiladeimatrix : use GGUF to store importance matrices (#9400)
next