How Fine-tuning Open Source LLMs Solves GenAI Productionization - Piero Molino | Stanford MLSys #94
54:36
Towards Conversational Diagnostic AI - Khaled Saab | Stanford MLSys #95
1:19:06
Hardware-aware Algorithms for Sequence Modeling - Tri Dao | Stanford MLSys #87
1:01:18
5 Reasons Why Adapters are the Future of Fine-tuning LLMs
1:16:48
Notes on AI Hardware - Benjamin Spector | Stanford MLSys #88
1:25:40
Modernizing VFX, Animation & Game Pipelines: Introducing K8 & Pulumi for Container Management
58:30
Snowflake + Predibase: Smaller, faster & cheaper LLMs that beat GPT-4
59:53
Efficient Fine-Tuning for Llama-v2-7b on a Single GPU
59:21