All
5+
10+
25+
50+
100+
2
Baseten raises $150M Series D at $2.15B (fortune.com)
a week ago |
philipkiely
| fortune.com
|
newest
100
Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs (baseten.co)
a month ago |
philipkiely
| baseten.co
|
best
1
How to build function calling and JSON mode for open-source and fine-tuned LLMs (baseten.co)
a year ago |
philipkiely
| baseten.co
|
newest
2
How to double tokens per second for Llama 3 with Medusa (baseten.co)
a year ago |
philipkiely
| baseten.co
|
newest
1
FP8: Efficient model inference with 8-bit floating point numbers (baseten.co)
a year ago |
philipkiely
| baseten.co
|
newest
1
Three techniques to adapt LLMs for any use case (baseten.co)
2 years ago |
philipkiely
| baseten.co
|
newest
5
Serving four million Riffusion requests in two days (baseten.co)
2 years ago |
philipkiely
| baseten.co
|
newest
12
Show HN: Free Stable Diffusion 2.0 hosted interface (baseten.co)
2 years ago |
philipkiely
| baseten.co
|
frontpage
4
Try it yourself: Speech to text with Whisper (baseten.co)
2 years ago |
philipkiely
| baseten.co
|
newest
2
Deploying Stable Diffusion in Production Using Truss
3 years ago |
philipkiely
| baseten.co
|
newest
4
Hosted Stable Diffusion Demo
3 years ago |
philipkiely
| baseten.co
|
newest
8
Show HN: Truss – Serve any ML model without boilerplate code
3 years ago |
philipkiely
| github.com
|
frontpage