auto-round
09d3dec1
- Skip fused_moe replacement when llm-compressor oneshot already linearizes experts (#1966)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
95 days ago
Skip fused_moe replacement when llm-compressor oneshot already linearizes experts (#1966) Signed-off-by: changwangss <chang1.wang@intel.com>
References
#1966 - Skip fused_moe replacement when llm-compressor oneshot already linearizes experts
Author
changwangss
Parents
3ab95207
Loading