Update nvfp4_experts_only to use dequantized BF16 model

2026-05-07 16:34:37 +00:00
parent b5d14aa8b8
commit cbfc5a9afb
1 changed files with 1 additions and 1 deletions
--- a/scripts/model_opt_nvfp4_experts_only.py
+++ b/scripts/model_opt_nvfp4_experts_only.py
@@ -30,7 +30,7 @@ import sys
 import os

 # ── Config ──────────────────────────────────────────────────────────────────
-MODEL = "/root/nvidia-meeting/DeepSeek-V4-Pro"  # Mixed-precision source
+MODEL = "/root/nvidia-meeting/DeepSeek-V4-Pro-BF16"  # Dequantized BF16 (from scripts/dequant_fp8_to_bf16.py)
 QUANT = "nvfp4_experts_only"
 TP = 8
 CALIB = 256