Hacker News new | past | comments | ask | show | jobs | submit | gdiamos's submissions login
1. Notes on Building LLMs in 2024
4 points by gdiamos 9 days ago | past | discuss
2. LLM Inference at the Memory Wall (lamini.ai)
1 point by gdiamos 25 days ago | past
3. LLMs hallucinate in critical enterprise scenarios (lamini.ai)
6 points by gdiamos 6 months ago | past | 1 comment
4. Training LLMs in the Wild Wild West – AMD multi-node (lamini.ai)
2 points by gdiamos 6 months ago | past
5. Open source ICD11 Mistral trained on AMD GPUs [video] (youtube.com)
2 points by gdiamos 8 months ago | past | 1 comment
6. Good old fashion ML is dying
20 points by gdiamos 10 months ago | past | 16 comments
7. AI startup Lamini bets future on AMD's Instinct GPUs (theregister.com)
22 points by gdiamos on Sept 26, 2023 | past | 6 comments
8. How to use a LLM to classify text (github.com/lamini-ai)
2 points by gdiamos on Sept 23, 2023 | past | 1 comment
9. Laminify: Instantly classify data with Lamini and Llama 2 (github.com/lamini-ai)
2 points by gdiamos on Sept 20, 2023 | past | 2 comments
10. Cramming an LLM platform into one container (lamini-ai.github.io)
3 points by gdiamos on Aug 24, 2023 | past | 1 comment
11. 1.109B times faster serving of finetuned LLMs (lamini.ai)
2 points by gdiamos on Aug 17, 2023 | past | 1 comment
12. Specializing LLMs on Databricks (databricks.com)
3 points by gdiamos on June 15, 2023 | past
13. MLPerf Releases Inference Results (mlperf.org)
2 points by gdiamos on Nov 6, 2019 | past | 1 comment

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: