Updating lm-format-enforcer version and adding links to decoding libraries in docs (#4222)

2024-04-20 11:33:16 +03:00
parent 91528575ec
commit cc74b2b232
3 changed files with 8 additions and 4 deletions
--- a/vllm/model_executor/layers/quantization/fp8.py
+++ b/vllm/model_executor/layers/quantization/fp8.py
@@ -1,4 +1,4 @@
-from typing import Any, Dict, List, Optional
+from typing import Any, Dict, List, Optional, Tuple

 import torch
 from torch.nn import Module
@@ -114,7 +114,7 @@ class Fp8LinearMethod(LinearMethodBase):
        return output


-def per_tensor_quantize(tensor: torch.Tensor) -> tuple[torch.Tensor, float]:
+def per_tensor_quantize(tensor: torch.Tensor) -> Tuple[torch.Tensor, float]:
    """Quantize a tensor using per-tensor static scaling factor.

    Args: