Every story and comment from the Hacker News API, in a layout borrowed from 2001.
A comment on Accelerating Gemma 4: faster inference with multi-token prediction drafters.
https://github.com/vllm-project/vllm/pull/41745
("Add Gemma4 MTP speculative decoding support")
There are no comments on this comment yet.
https://github.com/vllm-project/vllm/pull/41745
("Add Gemma4 MTP speculative decoding support")