text-generation-inference
64142489
- Add support for fused MoE Marlin for AWQ (#2616)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
1 year ago
Add support for fused MoE Marlin for AWQ (#2616) * Add support for fused MoE Marlin for AWQ This uses the updated MoE Marlin kernels from vLLM. * Add integration test for AWQ MoE
References
#2616 - Add support for fused MoE Marlin for AWQ
Author
danieldk
Parents
8b295aa4
Loading