John Smith
|
4906961bf1
|
fix bug
|
2023-03-23 23:37:39 +08:00 |
Forkoz
|
58998acc9f
|
Fix cuda kernel for Pascal & Cuda 6/6.1
When I left the other functions to use normal atomic add it seemed like a small speedup. 4.79 it/s vs 5.23 it/s
|
2023-03-23 07:33:57 -05:00 |
|
John Smith
|
3471be4e56
|
add fast_4bit_matmul and auto switch 2 methods according to bottleneck
|
2023-03-21 08:43:07 +00:00 |
|
John Smith
|
5b64833390
|
add half support on cuda kernel
|
2023-03-20 09:19:05 +00:00 |
|
John Smith
|
551f62a0e8
|
add patch for gptq and peft
|
2023-03-18 13:31:48 +08:00 |