Local UI to run and train LLMs and diffusion models. Supports GGUF, MLX, Qwen3.8, DeepSeek-V4.1, MiniMax-H3, Gemma 4, FLUX and more.
Python agentaichatgptdeepseekfine-tuninggemmaimage-generationllamallmllmsopenaipythonqwenreinforcement-learningself-hostedstable-diffusiontext-to-speechttsuiunsloth
FP8 e4m3fn scale dequant: pass enable_fp_fusion like every other launch (#14969)
Daniel Hand95472002820
diff --git a/unsloth/kernels/fp8.py b/unsloth/kernels/fp8.pyindex 5d52a15f13a..31f7b9fee6f 100644--- a/unsloth/kernels/fp8.py+++ b/unsloth/kernels/fp8.py@@ -253,6 +253,7 @@ def _scale_dequant_one_pass(x: torch.Tensor, s: torch.Tensor, dtype: torch.dtypeROUND_SCALE = dtype != torch.float16,LONG_INDEXING = long_indexing(xb, out, block = BLOCK_M * n),num_warps = num_warps,+ enable_fp_fusion = True,)return out.t() if transposed else out