Histórico de Commits

Autor SHA1 Mensagem Data
  Xuan-Son Nguyen 55ac8c7791 server : (webui) revamp Settings dialog, add Pyodide interpreter (#11759) há 11 meses atrás
  Woof Dog e6e6583199 server : (webui) increase edit textarea size (#11763) há 11 meses atrás
  Georgi Gerganov aaa5505307 server : minor log updates (#11760) há 11 meses atrás
  Georgi Gerganov bdcf8b6a56 cont : fix mmap flag print (#11699) há 11 meses atrás
  Karol Kontny 4d3465c5ae ggml: Fix data race in ggml threadpool (#11736) há 11 meses atrás
  Johannes Gäßler d80be897ac CUDA: fix min. version for movmatrix (#11751) há 11 meses atrás
  Nikolaos Pothitos 3ab410f55f readme : update front-end framework (#11753) há 11 meses atrás
  Xuan-Son Nguyen 0cf867160c server : (webui) fix numeric settings being saved as string (#11739) há 11 meses atrás
  Eric Curtin d2fe216fb2 Make logging more verbose (#11714) há 11 meses atrás
  Georgi Gerganov ed926d8833 llama : fix defrag logic (#11707) há 11 meses atrás
  Christian Fillion 2d219b389e vocab : ignore invalid UTF-8 input in the BPE tokenizer (#11729) há 11 meses atrás
  magicse 333820d749 llama : fix progress dots (#11730) há 11 meses atrás
  Jeff Bolz c026ba3c23 vulkan: print shared memory size (#11719) há 11 meses atrás
  Christian Fillion 7ee953a64a llama : add llama_sampler_init for safe usage of llama_sampler_free (#11727) há 11 meses atrás
  Akarshan Biswas ec3bc8270b SYCL: remove XMX info from print devices (#11712) há 11 meses atrás
  Daniel Bevenius b7552cfcbc common : add default embeddings presets (#11677) há 11 meses atrás
  Jinyang He 225bbbfa39 ggml : optimize and build warning fix for LoongArch (#11709) há 11 meses atrás
  tv1wnd 855cd0734a llama : fix old glm4 models (#11670) há 11 meses atrás
  Georgi Gerganov 8a59053f63 sync : ggml há 11 meses atrás
  Patrick Peng 1d20e53c40 rpc: fix known RCE in rpc-server (ggml/1103) há 11 meses atrás
  Xuan-Son Nguyen 2fb3c32a16 server : (webui) migrate project to ReactJS with typescript (#11688) há 11 meses atrás
  Tei Home 9ab42dc722 docs: update fedora cuda guide for 12.8 release (#11393) há 11 meses atrás
  Akarshan Biswas 194b2e69f8 SYCL: Adjust support condition for norm operators (#11674) há 11 meses atrás
  Georgi Gerganov 9dd7a0390f llama : add log about loading model tensors (#11699) há 11 meses atrás
  Adrien Gallouët c0d4843225 build : fix llama.pc (#11658) há 11 meses atrás
  junchao-zhao 8d4d2be143 ggml : fix LoongArch compile error with 128-bit SIMD (#11701) há 11 meses atrás
  Jeff Bolz 2c6c8df56d vulkan: optimize coopmat2 iq2/iq3 callbacks (#11521) há 11 meses atrás
  Rémy O 8a7e3bf17a vulkan: initial support for IQ4_XS quantization (#11501) há 11 meses atrás
  Jeff Bolz 1b598b3058 vulkan: use smaller combined allocations to avoid fragmentation (#11551) há 11 meses atrás
  Charles Duffy 902368a06b metal : avoid breaking build when metal API predates TARGET_OS_VISION (#11690) há 11 meses atrás