Show HN: VLM Inference Engine in Rust
1 points
1 hour ago
| 1 comment
| mixpeek.com
| HN
storystarling
21 minutes ago
[-]
What hardware are you running this on to get 2-3s latency? A 14GB model plus KV cache seems like it would require a 24GB card (3090/4090) to avoid swapping. I've found that once you spill over to system RAM on consumer gear the performance usually falls off a cliff.
reply