Historique des commits

Auteur SHA1 Message Date
  Nauful Shaikh b772394297 server : webui : Upgrade daisyui, tailwindcss. (#12735) il y a 10 mois
  nick huang 23106f94ea gguf-split : --merge now respects --dry-run option (#12681) il y a 10 mois
  Nicolò Scipione 94148ba330 sycl: allow ggml-sycl configuration and compilation using Visual Studio project/solution (#12625) il y a 10 mois
  Ronny Brendel 9ac4d611d0 cmake: fix ggml-shaders-gen compiler paths containing spaces (#12747) il y a 10 mois
  Daniel Bevenius 348888e0dc docs : add XCFramework section to README.md [no ci] (#12746) il y a 10 mois
  Jeff Bolz 74d4f5b041 vulkan: Hybrid waitForFences/getFenceStatus to reduce fence latency (#12630) il y a 10 mois
  Jeff Bolz 35e592eb30 vulkan: set cmake minimum and project name in vulkan-shaders (#12744) il y a 10 mois
  lhez 7d7b1bafa7 opencl: update doc for OpenCL (#12702) il y a 10 mois
  Gaurav Garg c262beddf2 CUDA: Prefer vector flash decoding kernel for Gemma models (#12738) il y a 10 mois
  yumeyao 5dd5d1ab00 vocab : use string_view::find() to avoid unnecessary looking up beyond the fragment range (#12706) il y a 10 mois
  Jeff Bolz 1c059995e0 vulkan: Fix missing cmake logic for dot product extension (#12721) il y a 10 mois
  Atharva Dubey 2004644b7a ci : add env variable in ggml-ci and document the same in SYCL.md (#12736) il y a 10 mois
  R0CKSTAR 5f696e88e0 sync : minja (inclusionAI/Ling) and update tests (#12699) il y a 10 mois
  a3sh 193c3e03a6 fix MUSA compiler warning (#12704) il y a 10 mois
  Chenguang Li 65cfe136a0 CANN: Support operator SIN COS ARGMAX (#12709) il y a 10 mois
  Alan Gray 3f9da22c2b Simplify and improve CUDA graphs through use of indirect copy pointers (#9017) il y a 10 mois
  hipudding 2a0dc97e56 CANN: Fix failed test cases (#12708) il y a 10 mois
  lhez 97a20c012b opencl: use `max_alloc_size` in backend ctx instead of querying again (#12705) il y a 10 mois
  Jeff Bolz f01bd02376 vulkan: Implement split_k for coopmat2 flash attention. (#12627) il y a 10 mois
  bandoti 6f3bd38640 cmake: remove caching from vulkan coopmat checks (#12719) il y a 10 mois
  Jeff Bolz be0a0f8cae vulkan: Implement grouped query attention in the coopmat2 FA shader (#12559) il y a 10 mois
  0cc4m 92e3006bb6 Vulkan: Fix mmq int dot float cache size (#12722) il y a 10 mois
  Georgi Gerganov 833e2b7409 model : print tensor size during load (#12711) il y a 10 mois
  Diego Devesa e0e912f49b llama : add option to override model tensor buffers (#11397) il y a 10 mois
  Georgi Gerganov a10b36c91a llama : refactor kv cache guard (#12695) il y a 10 mois
  Sigbjørn Skjæret 83a88bd6af vocab : BailingMoE : change possessive quantifiers to greedy (#12677) il y a 10 mois
  Xuan-Son Nguyen 42eb248f46 common : remove json.hpp from common.cpp (#12697) il y a 10 mois
  Chenguang Li 9bacd6b374 [CANN] get_rows and dup optimization (#12671) il y a 10 mois
  Xuan-Son Nguyen 267c1399f1 common : refactor downloading system, handle mmproj with -hf option (#12694) il y a 10 mois
  Junil Kim f423981ac8 opencl : fix memory allocation size (#12649) il y a 10 mois