Commit History

Author SHA1 Message Date
  Xuan-Son Nguyen 7c727fbe39 arg : add --no-mmproj-offload (#13093) 9 months ago
  Xuan-Son Nguyen 80982e815e arg : clean up handling --mmproj with -hf (#13082) 9 months ago
  Georgi Gerganov 7604a7d6b8 metal : fix floating-point range of attention scores in FA kernels (#13090) 9 months ago
  Eve b3b6d862cf vulkan: matmul gcn tuning (#13016) 9 months ago
  pl752 5630406959 llama-mtmd-cli: Sigint rework in mtmd vision example (#13080) 9 months ago
  Xuan-Son Nguyen ecda2ec4b3 mtmd : Support Pixtral 12B (#13065) 9 months ago
  piDack eb1776b15a convert : Append mult-eos,half-rope,bos to GLM4-0414 and Z (#13021) 9 months ago
  Radoslav Gerganov 2cca6c01e4 rpc : add command line option for number of threads for the CPU backend (#13060) 9 months ago
  Johannes Gäßler 658987cfc9 CUDA: noncont MMVQ + batched bs1 MUL_MAT_ID (#13014) 9 months ago
  Xuan-Son Nguyen dc39a5e7a8 mtmd : support SmolVLM (version 1 and 2) (#13050) 9 months ago
  Georgi Gerganov ab47dec3d3 security : add note about RPC and server functionality (#13061) 9 months ago
  Georgi Gerganov 7b53389c24 metal : add memory pool for temp allocs (#12850) 9 months ago
  Xuan-Son Nguyen 243453533e llava : update documentations (#13055) 9 months ago
  Diego Devesa 1d735c0b4f ggml : add SSE 4.2 and x64 base variant for CPUs without AVX (#12871) 9 months ago
  Akarshan Biswas 5368ddda7a SYCL: Add non-contiguous support in ROPE (#12993) 9 months ago
  Xuan-Son Nguyen 84a9bf2fc2 mtmd : merge llava, gemma3 and minicpmv CLI into single `llama-mtmd-cli` (#13012) 9 months ago
  Xuan-Son Nguyen 2016f07bd1 convert : experimental support for `--mmproj` flag (#13023) 9 months ago
  Jeffrey Morgan 6602304814 llava: fix errors in clip.h on certain compilers (#13030) 9 months ago
  Jeff Bolz 66168204be vulkan: support noncontiguous rms_norm (#13031) 9 months ago
  Jeffrey Morgan 4ba9d711ba metal: add neg operator (#13029) 9 months ago
  bandoti 00137157fc Disable CI cross-compile builds (#13022) 9 months ago
  Sigbjørn Skjæret fb28f4f80e gguf-py : fix upload python package workflow (#13020) 9 months ago
  Xuan-Son Nguyen 37b9f0d29d clip : refactor, add `image_manipulation` and `llava_uhd` classes (#13011) 9 months ago
  Daniel Tang 6408210082 main : Fix Ctrl+D/newline handling (#12951) 9 months ago
  Chris Thompson aff9d107b0 gguf-py : GGUF Editor GUI - Python + Qt6 (#12930) 9 months ago
  Xuan-Son Nguyen 35370ba945 server : use std::move whenever possible (#12936) 9 months ago
  Akarshan Biswas 8d66005763 SYCL: Refactor and enable FP16 in binary broadcast OPs (#12975) 9 months ago
  Xuan-Son Nguyen b9154ecff9 mtmd : add methods to access `mtmd_image_tokens` (#12906) 9 months ago
  Radoslav Gerganov 2db9ba1464 rpc : add RPC_CMD_HELLO (#12955) 9 months ago
  Georgi Gerganov 2f74c354c0 graph : make FA compatible with MLA + add initial Metal kernels (#12953) 9 months ago