biondizzle/deepseek-v4-quant
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
f2656dcf6d4013adf8ee7e05ab5be36dc3ef4604
deepseek-v4-quant/scripts/dequant_fp8_to_bf16.py
biondizzle b70a04696e Add resume capability to dequant script (skip already-done shards) 
Verified our FP4 dequant is byte-identical to official transformers
MXFP4 implementation. Max diff = 0.0 across all values.
2026-05-08 02:58:24 +00:00

11 KiB
Raw Blame History

View Raw
Reference in New Issue View Git Blame Copy Permalink