transformers
bdf5fb70
- Skip non-selected experts for qwen3_moe (#38133)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
304 days ago
Skip non-selected experts for qwen3_moe (#38133) * fix(qwen3moe): skip experts with no workload * avoid tolist and also update other moe models * fix: should squeeze 0-dim only
References
#38133 - Skip non-selected experts for qwen3_moe
Author
seven-mile
Parents
719058c6
Loading