llama.cpp
d3064fdd
- convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) (#32476)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 day ago
convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8) (#32476) * convert : fix FP8 n-gram table export for qwen4exp * convert : dequantize block-scaled FP8 weight_scale_inv in ModelOpt checkpoints
References
#32476 - convert : fix FP8 qwen4exp checkpoints (n-gram table scale, block-scaled FP8)
Author
am17an
Parents
7f106b54
Loading