deepseekmirror/DeepSeek-V3
1
0
Fork 0
mirror of https://github.com/deepseek-ai/DeepSeek-V3.git synced 2025-02-22 13:48:56 -05:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

fix comment

Browse Source
This commit is contained in:
Xingkai Yu 2025-02-07 16:42:55 +08:00 committed by GitHub
parent 1d7d440461
commit 5ee97a83f0
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
inference/model.py
View File

@ -143,7 +143,7 @@ def linear(x: torch.Tensor, weight: torch.Tensor, bias: Optional[torch.Tensor] =
quantization-aware computations depending on the input parameters.
Notes:
- If `weight` is quantized (e.g., `element_size() > 1`), a dequantized version
- If `weight` is quantized (e.g., `element_size() == 1`), a dequantized version
is used for computation.
- If `gemm_impl == "bf16"`, dequantization and a `bf16` GEMM operation are applied.
- For other cases, the function applies quantization to `x` and uses `fp8_gemm` for computation.