vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

0 releases 3,056 tags

RSS feed
  • vbatts-gguf-2023-sept da0400344b

    ggml-cuda : perform cublas fp16 matrix multiplication as fp16 (#3370)
    Some checks failed
    Code Coverage / run (push) Has been cancelled
    Details

    Ghost released this 2023-09-28 10:08:28 +00:00 | 3401 commits to master since this release

    • ggml-cuda : perform cublas fp16 matrix multiplication as fp16

    • try to fix rocm build

    • restrict fp16 mat mul to volta and up

    Downloads