philipkiely
- Karma
- 1,112
- Created
- 7 years ago
About
DevRel @ https://baseten.coEmail me: username at baseten.co
Recent Submissions
- 1. ▲ Baseten raises $150M Series D at $2.15B (fortune.com)
- 2. ▲ Running GPT-OSS-120B at 500 tokens per second on Nvidia GPUs (baseten.co)
- 3. ▲ How to build function calling and JSON mode for open-source and fine-tuned LLMs (baseten.co)
- 4. ▲ How to double tokens per second for Llama 3 with Medusa (baseten.co)
- 5. ▲ FP8: Efficient model inference with 8-bit floating point numbers (baseten.co)