GPU-accelerated token generation (new quantization format)#1412
Merged
ggerganov merged 9 commits intoggerganov:masterfrom JohannesGaessler:dequantize-matmul-4May 13, 2023
+336-42
Commits
Commits on May 12, 2023
Commits on May 13, 2023
- committed
- committed
- committed
- committed
- committed
