Chris Fregly

Engineering and Product Leader (ex-AWS, Databricks, Netflix)

[Chris Fregly @cfregly]

YouTube: https://t.co/6ijBvWDHzc

[Chris Fregly @cfregly]

Join me and @anbarth today at 9am PT to talk about @OpenAI on @awscloud, @cerebras vs. @nvidia vs. @Google TPU, and high-performance KV-cache offloading with @weka !!! https://t.co/22wOApbpCn

[Chris Fregly @cfregly]

Zoom: https://t.co/JcjLr4brXU

[levi @levidiamode]

- Link to @cfregly's GTC recap: https://t.co/9foYoKcPqa
- Link to Understanding AMD's ISA talk: https://t.co/sBa1Ws3gKc
- Link to HIP intro: https://t.co/hnjJOVA0lh
- Link to another HIP intro: https://t.co/3TNJZKmPhu
- Link to panel discussion between Jeff Dean and Bill Daly: https://t.co/H11jfKSLoN
- Link to Kimi K2.5 talk: https://t.co/yLbXfZO5gI

[Chris Fregly @cfregly]

https://t.co/ylrIigvpwn

[Chris Fregly @cfregly]

Join me today at 9am PT for an awesome set of talks on performance highlights from @nvidia GTC 2026 and AI Inference including disaggregated refill-decode with NVIDIA GPUs and RadixAttention https://t.co/s6dz06g4N3

[Chris Fregly @cfregly]

Arguably the most disturbing prop here @nvidia GTC

[Chris Fregly @cfregly]

@swyx @NVIDIAGTC @NVIDIAAIDev Jensen’s fave slide, apparently!

[Chris Fregly @cfregly]

25 google slides that summarize the NVIDIA GTC 2026 Keynote: https://t.co/9GLZctO4FB Love the country-music and OpenClaw themes!! 🤠🦞 @NVIDIAAIDev @NVIDIAAI @nvidia

[Chris Fregly @cfregly]

Hot take from Day 0 at NVIDIA GTC: NVLink (NVIDIA proprietary high-speed GPU-to-GPU interconnect) actually uses InfiniBand under the hood!? 🤯

[Chris Fregly @cfregly]

Was waiting for this… https://t.co/LHnGomgmYw

[GPU MODE @GPU_MODE]

We're celebrating our 100th lecture with @SemiAnalysis_ tomorrow at 9am PST and we'll be talking about arguably the most important OSS benchmark suite out today InferenceX

Time flies, thank you to everyone who stuck around for this long 🥲

[MLOps Community @mlopscommunity]

Just wrapped a conversation on performance optimization and software/hardware co-design across PyTorch, CUDA, and NVIDIA GPUs with @cfregly.

[Chris Fregly @cfregly]

Github Repo: https://t.co/yQZFuDdlvh
O'Reilly Book: https://t.co/YZRGb1LLqn
Course: https://t.co/Mvo7AhV1w7
YouTube link: https://t.co/ImNyoD5lKo

[Chris Fregly @cfregly]

Join us now for the a great set of talks on hashtag#OpenClaw, NVIDIA's NVFP4 numeric format, and a new course on AI Performance Engineering with Riccardo Mereu from Verda and Stan from Nebius!
https://t.co/hErvyZG1VR

[Chris Fregly @cfregly]

@steipete @OpenAI @openclaw Hell yeah