| | 256K context with 72MiB of KV cache on the GPU (github.com/luce-org) |
| 3 points by GreenGames 46 days ago | past |
|
| | PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090 (github.com/luce-org) |
| 3 points by GreenGames 3 months ago | past | 1 comment |
|
| | [flagged] We got 207 tok/s with Qwen3.5-27B on an RTX 3090 (github.com/luce-org) |
| 165 points by GreenGames 3 months ago | past | 52 comments |
|
| | Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090 (github.com/luce-org) |
| 6 points by GreenGames 3 months ago | past | 1 comment |
|
