philipkiely

DevRel @ https://baseten.co

Email me: username at baseten.co

Posts

• How to build function calling and JSON mode for open-source and fine-tuned LLMs
  by philipkielyon 9/12/2024, 4:21 PMwith 0 comments
• How to double tokens per second for Llama 3 with Medusa
  by philipkielyon 8/20/2024, 2:09 PMwith 0 comments
• FP8: Efficient model inference with 8-bit floating point numbers
  by philipkielyon 3/8/2024, 4:12 PMwith 0 comments
• Three techniques to adapt LLMs for any use case
  by philipkielyon 6/15/2023, 5:38 PMwith 0 comments
• Serving four million Riffusion requests in two days
  by philipkielyon 12/21/2022, 5:44 PMwith 0 comments
• Show HN: Free Stable Diffusion 2.0 hosted interface
  by philipkielyon 11/24/2022, 10:05 PMwith 2 comments
• Try it yourself: Speech to text with Whisper
  by philipkielyon 10/1/2022, 9:38 PMwith 0 comments
• Deploying Stable Diffusion in Production Using Truss
  by philipkielyon 9/1/2022, 9:41 PMwith 0 comments
• Hosted Stable Diffusion Demo
  by philipkielyon 8/24/2022, 7:03 PMwith 0 comments
• Show HN: Truss – Serve any ML model without boilerplate code
  by philipkielyon 7/29/2022, 3:06 PMwith 9 comments
• Code generation interactive demo (Salesforce Codegen mono 2B)
  by philipkielyon 7/1/2022, 10:19 PMwith 0 comments