We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent 68d2542 commit a268e0cCopy full SHA for a268e0c
1 file changed
docs/guides/compression_formats.md
@@ -14,7 +14,7 @@ sparsity type. For more details on the quantization schemes, see
14
| W4A16 - float | None | nvfp4_pack_quantized | Dense |
15
| W4A4 - float | None | nvfp4_pack_quantized | Dense |
16
| W4A16 - int | None | pack_quantized | Dense |
17
-| W4A8 - int | None | int4_quantized | Dense |
+| W4A8 - int | None | int4_pack_quantized | Dense |
18
| W8A16 - int | None | pack_quantized | Dense |
19
| W8A16 - float | None | naive_quantized | Dense |
20
| W8A8 - int | 2:4 | int_quantized | Sparse24 |
0 commit comments