تاریخچه Commit ها

نویسنده SHA1 پیام تاریخ
  Michael Yang 7e33a017c0 partial offloading 1 سال پیش
  Daniel Hiltgen 1f11b52511 Refined min memory from testing 1 سال پیش
  Daniel Hiltgen 526d4eb204 Release gpu discovery library after use 1 سال پیش
  Michael Yang 91b3e4d282 update memory calcualtions 1 سال پیش
  Jeremy dfc6721b20 add support for libcudart.so for CUDA devices (adds Jetson support) 1 سال پیش
  Daniel Hiltgen 6c5ccb11f9 Revamp ROCm support 1 سال پیش
  Daniel Hiltgen be330174dd Allow setting max vram for workarounds 1 سال پیش
  Daniel Hiltgen 9754c6d9d8 Harden AMD driver lookup logic 1 سال پیش
  Daniel Hiltgen 6d84f07505 Detect AMD GPU info via sysfs and block old cards 1 سال پیش
  Daniel Hiltgen 4072b5879b Merge pull request #2246 from dhiltgen/reject_cuda_without_avx 1 سال پیش
  Daniel Hiltgen 15562e887d Don't disable GPUs on arm without AVX 1 سال پیش
  Daniel Hiltgen f07f8b7a9e Harden for zero detected GPUs 1 سال پیش
  Daniel Hiltgen e02ecfb6c8 Merge pull request #2116 from dhiltgen/cc_50_80 1 سال پیش
  Daniel Hiltgen 667a2ba18a Detect lack of AVX and fallback to CPU mode 1 سال پیش
  Daniel Hiltgen 9d7b5d6c91 Ignore AMD integrated GPUs 1 سال پیش
  Daniel Hiltgen 013fd07139 More logging for gpu management 1 سال پیش
  Daniel Hiltgen 987c16b2f7 Report more information about GPUs in verbose mode 1 سال پیش
  Daniel Hiltgen a447a083f2 Add compute capability 5.0, 7.5, and 8.0 1 سال پیش
  Jeffrey Morgan f32ea81b21 increase minimum overhead to 1024MiB (#2114) 1 سال پیش
  Daniel Hiltgen 681a914990 Add support for CUDA 5.2 cards 1 سال پیش
  Daniel Hiltgen 552db98bf1 More WSL paths 1 سال پیش
  Self Denial eb76f3e379 Fix CPU-only build under Android Termux enviornment. 1 سال پیش
  Daniel Hiltgen abec7f06e5 Merge pull request #2056 from dhiltgen/slog 1 سال پیش
  Daniel Hiltgen fedd705aea Mechanical switch from log to slog 1 سال پیش
  Alexander F. Rødseth f4bf1d514f Let gpu.go and gen_linux.sh also find CUDA on Arch Linux 1 سال پیش
  Daniel Hiltgen d88c527be3 Build multiple CPU variants and pick the best 1 سال پیش
  Daniel Hiltgen 8da7bef05f Support multiple variants for a given llm lib type 1 سال پیش
  Jeffrey Morgan b24e8d17b2 Increase minimum CUDA memory allocation overhead and fix minimum overhead for multi-gpu (#1896) 1 سال پیش
  Daniel Hiltgen 3c49c3ab0d Harden GPU mgmt library lookup 1 سال پیش
  Jeffrey Morgan c336693f07 calculate overhead based number of gpu devices (#1875) 1 سال پیش