fix fp8 multi gpu; update FQA

doc/en/FAQ.md

@@ -93,3 +93,7 @@ Traceback (most recent call last):
 RuntimeError: probability tensor contains either `inf`, `nan` or element < 0
 ```
 **SOLUTION**: The issue of running ktransformers on Ubuntu 22.04 is caused by the current system's g++ version being too old, and the pre-defined macros do not include avx_bf16. We have tested and confirmed that it works on g++ 11.4 in Ubuntu 22.04.
+
+### Q: Using fp8 prefill very slow.
+
+The FP8 kernel is build by JIT, so the first run will be slow. The subsequent runs will be faster.

ktransformers/ktransformers_ext/triton/fp8gemm.py

@@ -102,7 +102,8 @@ def weight_dequant(x: torch.Tensor, s: torch.Tensor, block_size: int = 128) -> t
     M, N = x.size()
     y = torch.empty_like(x, dtype=torch.get_default_dtype())
     grid = lambda meta: (triton.cdiv(M, meta['BLOCK_SIZE']), triton.cdiv(N, meta['BLOCK_SIZE']))
-    weight_dequant_kernel[grid](x, s, y, M, N, BLOCK_SIZE=block_size)
+    with torch.cuda.device(x.device):
+        weight_dequant_kernel[grid](x, s, y, M, N, BLOCK_SIZE=block_size)
     return y