Viewing profile — dramlord
dramlord
HN member- Joined
- Sun, Dec 17, 2023, 3:20 AM UTC
- HN karma
- 1
- Public activity
- 1 items
- HN profile
- View on Hacker News ↗
About dramlord
No profile information was provided.
Recent public activity
-
comment
Comment #38670073
You can amortize memory loading with large continuous batching. I imagine more compute would help the problem for certain workloads like speculative decoding