ASPD (Adaptive Serial-Parallel Decoding) is an end-to-end framework for accelerating LLM inference by exploiting intrinsic parallelism in autoregressive outputs.
-
Notifications
You must be signed in to change notification settings - Fork 0
TencentYoutuResearch/LLM-ASPD
About
ASPD (Adaptive Serial-Parallel Decoding) is an end-to-end framework for accelerating LLM inference by exploiting intrinsic parallelism in autoregressive outputs.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published