HK
Heykuki News
Top
New
Best
Ask
Show
Jobs
Toggle theme
Top
New
Best
Ask
Show
Jobs
Request
1.
▲
FlexGen: Running large language models on a single GPU
github.com/FMInference
43 comments
3 years ago
behnamoh
192 points
2.
▲
Beast: Inference Economy Inversion in Agentic Coding Systems
github.com/Byron2306
discuss
a day ago
Byron230686
2 points
3.
▲
Show HN: Alloy – a PyTorch backend and inference engine for Apple Silicon
github.com/rayanht
discuss
2 days ago
rayanht
2 points
4.
▲
Story of How Im Running an Unlimited $6/Month AI Provider on 4x RTX 3090s
3 comments
8 days ago
yolo-auto
8 points