HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
Show HN: OS Megakernel that match M5 Max Tok/w at 2x the Throughput on RTX 3090
github.com/Luce-Org
1 comment
2 months ago
GreenGames
6 points
2.
▲
We got 207 tok/s with Qwen3.5-27B on an RTX 3090
github.com/Luce-Org
52 comments
2 months ago
GreenGames
165 points
3.
▲
PFlash: 10x prefill speedup over llama.cpp at 128K on a RTX 3090
github.com/Luce-Org
1 comment
2 months ago
GreenGames
3 points
4.
▲
256K context with 72MiB of KV cache on the GPU
github.com/Luce-Org
discuss
6 days ago
GreenGames
3 points