Replace [silu_and_mul_]scaled_fp4_group_quant by Flashinfer equivalent (#12376)

2025-11-13 00:26:00 -08:00
parent c2d69e8b56
commit 6664083522
6 changed files with 42 additions and 39 deletions
@@ -48,6 +48,7 @@ SGLang supports various environment variables that can be used to configure its

 | Environment Variable | Description | Default Value |
 | `SGLANG_DEEPEP_BF16_DISPATCH` | Use Bfloat16 for dispatch | `"false"` |
+| `SGLANG_CUTEDSL_MOE_NVFP4_DISPATCH` | Use nvfp4 for dispatch | `"false"` |

 ## Memory Management