- 25 Jun, 2024 1 commit
-
-
Woo-Yeon Lee authored
[Speculative Decoding] Support draft model on different tensor-parallel size than target model (#5414)
-
- 05 Jun, 2024 1 commit
-
-
Nick Hill authored
-
[Speculative Decoding] Support draft model on different tensor-parallel size than target model (#5414)
