Day 1 of @icmlconf 2026 is here! ๐
The FriendliAI team is at Booth B115 all week โ come say hi.
We're the team behind continuous batching, and we spend our days making frontier open-weight model inference faster, cheaper, and more reliable. If that sounds like a problem you'd want to work on, we'd love to talk.
We're actively hiring across engineering and beyond. Stop by the booth to meet the team, ask us anything about inference, or just to have a chat.
๐ Open roles: https://t.co/862HK4fDIn
See you at B115!
#ICML2026 #Hiring #AIInference #FriendliAI
Open-source inference is efficient and interoperable, but managing deployments can be difficult.
At ๐๐ง๐, weโre demonstrating how to ๐ฐ๐ฑ๐ต๐ช๐ฎ๐ช๐ป๐ฆ ๐๐ ๐ธ๐ฐ๐ณ๐ฌ๐ญ๐ฐ๐ข๐ฅ๐ด, ๐ฃ๐ฆ๐ฏ๐ค๐ฉ๐ฎ๐ข๐ณ๐ฌ ๐๐ ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ๐ด, ๐ท๐ช๐ฃ๐ฆ ๐ค๐ฐ๐ฅ๐ฆ ๐ธ๐ช๐ต๐ฉ ๐ฐ๐ฑ๐ฆ๐ฏ-๐ธ๐ฆ๐ช๐จ๐ฉ๐ต ๐ฎ๐ฐ๐ฅ๐ฆ๐ญ๐ด, and ๐ด๐ค๐ข๐ญ๐ฆ ๐ค๐ฐ๐ฏ๐ต๐ข๐ช๐ฏ๐ฆ๐ณ๐ช๐ป๐ฆ๐ฅ ๐ช๐ฏ๐ง๐ฆ๐ณ๐ฆ๐ฏ๐ค๐ฆ.
Visit ๐๐ผ๐ผ๐๐ต ๐ฏ๐ฏ๐ฌ๐ฑ every day for 15 min technical deep dives on the hour, starting with:
๐ข ๐ญ๐ฃ๐ | ๐๐ ๐ช๐ผ๐ฟ๐ธ๐น๐ผ๐ฎ๐ฑ ๐ข๐ฝ๐๐ถ๐บ๐ถ๐๐ฎ๐๐ถ๐ผ๐ป: Implement continuous batching and online quantization to enhance performance.
๐ข ๐ฎ๐ฃ๐ | ๐ ๐ผ๐ฑ๐ฒ๐น ๐๐ฒ๐ป๐ฐ๐ต๐บ๐ฎ๐ฟ๐ธ๐ถ๐ป๐ด: Run high-speed benchmarks using the Friendli Suite.
๐ข ๐ฏ๐ฃ๐ | ๐ฉ๐ถ๐ฏ๐ฒ ๐๐ผ๐ฑ๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐ข๐ฝ๐ฒ๐ป-๐ช๐ฒ๐ถ๐ด๐ต๐ ๐บ๐ผ๐ฑ๐ฒ๐น๐: Use coding agents like Claude Code and @kilocode with models like GLM running on FriendliAI.
๐ข ๐ฐ๐ฃ๐ | ๐ฆ๐ฐ๐ฎ๐น๐ถ๐ป๐ด ๐๐ถ๐๐ต ๐๐ช๐ฆ: Run Containerized Inference with FriendliAI and AWS EKS
Want to learn more? Schedule a dedicated 15 min demo with our technical team find out how you can deliver ๐ฎ๐ซ-๐ฏ๐ซ throughput while reducing GPU costs by ๐ฑ๐ฌ-๐ต๐ฌ%: https://t.co/g69cagAU6W