architecture · first seen 12 Nov 2026
serverless LLM inference
Running large language model inference on demand in serverless platforms that start model workers dynamically.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Fast Serverless LLM Cold Starts by Sharing and Prewarming Startup WorkPapers · 12 Nov 2026 · Hongjin Kim, Igjae Kim, Kwanghoon Choi, Minho Ha, Jaehyuk Huh
Latest sources
- Fast Serverless LLM Cold Starts by Sharing and Prewarming Startup WorkPapers · 12 Nov 2026 · Hongjin Kim, Igjae Kim, Kwanghoon Choi, Minho Ha, Jaehyuk Huh