text-generation-inference
880ab9c2
- Add Flash decoding kernel ROCm (#2855)
Go
Login via GitHub
Home
Pricing
FAQ
Install
Login
via GitHub
Commit
View On
GitHub
Commit
339 days ago
Add Flash decoding kernel ROCm (#2855) * (vllm) updated vllm rocm kernels * revert silu * update partition size * remove grouped_topk * (nit) remove log * add flash decoding
References
#2855 - Add Flash decoding kernel ROCm
Author
mht-sharma
Parents
1660154a
Loading