auto-round
1f16c07e
- Implement hydration of scale tensors from sibling shards in FP8 dequantization
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
9 days ago
Implement hydration of scale tensors from sibling shards in FP8 dequantization Signed-off-by: Xin He <xin3.he@intel.com>
References
#2123 - [Experimental] Add NVFP4 E5M3 support and related components for model-free quantization
Author
xin3he
Parents
fa73368b
Loading