Commit History

Автор SHA1 Съобщение Дата
  Radoslav Gerganov 2cca6c01e4 rpc : add command line option for number of threads for the CPU backend (#13060) преди 9 месеца
  Johannes Gäßler 658987cfc9 CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014) преди 9 месеца
  Xuan-Son Nguyen dc39a5e7a8 mtmd : support SmolVLM (version 1 and 2) (#13050) преди 9 месеца
  Georgi Gerganov ab47dec3d3 security : add note about RPC and server functionality (#13061) преди 9 месеца
  Georgi Gerganov 7b53389c24 metal : add memory pool for temp allocs (#12850) преди 9 месеца
  Xuan-Son Nguyen 243453533e llava : update documentations (#13055) преди 9 месеца
  Diego Devesa 1d735c0b4f ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (#12871) преди 9 месеца
  Akarshan Biswas 5368ddda7a SYCL: Add non-contiguous support in ROPE (#12993) преди 9 месеца
  Xuan-Son Nguyen 84a9bf2fc2 mtmd : merge llava, gemma3 and minicpmv CLI into single `llama-mtmd-cli` (#13012) преди 9 месеца
  Xuan-Son Nguyen 2016f07bd1 convert : experimental support for `--mmproj` flag (#13023) преди 9 месеца
  Jeffrey Morgan 6602304814 llava: fix errors in clip.h on certain compilers (#13030) преди 9 месеца
  Jeff Bolz 66168204be vulkan: support noncontiguous rms_norm (#13031) преди 9 месеца
  Jeffrey Morgan 4ba9d711ba metal: add neg operator (#13029) преди 9 месеца
  bandoti 00137157fc Disable CI cross-compile builds (#13022) преди 9 месеца
  Sigbjørn Skjæret fb28f4f80e gguf-py : fix upload python package workflow (#13020) преди 9 месеца
  Xuan-Son Nguyen 37b9f0d29d clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011) преди 9 месеца
  Daniel Tang 6408210082 main : Fix Ctrl+D/newline handling (#12951) преди 9 месеца
  Chris Thompson aff9d107b0 gguf-py : GGUF Editor GUI - Python + Qt6 (#12930) преди 9 месеца
  Xuan-Son Nguyen 35370ba945 server : use std::move whenever possible (#12936) преди 9 месеца
  Akarshan Biswas 8d66005763 SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975) преди 9 месеца
  Xuan-Son Nguyen b9154ecff9 mtmd : add methods to access `mtmd_image_tokens` (#12906) преди 9 месеца
  Radoslav Gerganov 2db9ba1464 rpc : add RPC_CMD_HELLO (#12955) преди 9 месеца
  Georgi Gerganov 2f74c354c0 graph : make FA compatible with MLA + add initial Metal kernels (#12953) преди 9 месеца
  Alan Gray 207c22ec2d ggml: Re-enable CUDA graphs in presence of CONT and DUP nodes (#12970) преди 9 месеца
  hipudding 7a395f67a7 CANN: Add support for async operator submission (#12864) преди 9 месеца
  Mikko Juola 971f245b3b llama : recognize IBM Granite 3.3 FIM tokens (#12988) преди 9 месеца
  kimminsu 12b17501e6 opencl: fix incorrect local_size index in profiling log (#12868) преди 9 месеца
  Jeff Bolz 015022bb53 vulkan: enable coopmat2 FA gqa and split_k optimizations more often (#12931) преди 9 месеца
  Chenguang Li b43d89e311 CANN: Add 310P operator support check (#12962) преди 9 месеца
  lhez 80f19b4186 opencl: split `ggml-opencl.cl` into multiple files and cleanup (#12886) преди 9 месеца