Enjoy family, food, outdoors. On week days I spend time in my dining-room/office working on HW/SW/Systems for AI acceleration...
San Francisco
Joined February 2009
- Tweets120
- Following340
- Followers290
- Likes181
Cormac Brick retweeted
Build agentic workflows completely offline.
The Antigravity SDK now supports local execution with Gemma 4 and LiteRT. Run agents entirely on your local machine with:
💵 Zero token costs
🔒 Total data privacy
🔌 Offline reliability
Bonus feature: Support for OpenAI-compatible endpoints. Use Ollama, llama.cpp, vLLM and more to serve Gemma 💪
Get started: pip install google-antigravity litert-lm
Read the details: developers.googleblog.com/in…
Cormac Brick retweeted
i guess this is a great time to note that @cormacb's talks and workshops were some of the most popular @GoogleDeepMind sessions EVER!
we're so glad to work with @osanseviero and @vadiamit in presenting AIE Europe, including a super well received keynote from @RaiaHadsell.
Cormac returned with @benoitschilling for the World's Fair - videos launching today, see below 👇
Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps.
pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second.
That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket.
Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack.
Watch and save it, then fine-tune your own tiny agent tonight.
Thanks for highlighting my talk.
Tiny models do take a bit more work, but are well worth the effort!
Google engineer explained how to fine-tune a tiny LLM from 46% to 90% accuracy on your phone in 21 minutes - better than $1500 on-device AI bootcamps.
pick Gemma 270M -> generate synthetic task data -> fine-tune with LoRA -> quantize to int4 -> deploy to Pixel and hit 2000 tokens per second.
That loop is how a 270M model beats a 70B one on your task, running fully offline in your pocket.
Gemma 270M + synthetic data + LoRA + int4 quantization + on-device runtime - that's the stack.
Watch and save it, then fine-tune your own tiny agent tonight.
Amazing to see such great community momentum with Gemma4. Our team worked closely with Gemma team to ensure this runs well on lots of devices.
developers.google.com/edge/g…
Cormac Brick retweeted
TLMs: Tiny LLMs and Agents on Edge Devices with @cormacb
youtube.com/watch?v=-TiET_K-…
Function Gemma ships at 270 million parameters and runs nearly 2,000 tokens per second prefill on a Pixel 7. Out of the box, it hits 46% accuracy on a fixed set of app intents. Fine tune on a synthetically generated dataset and that clears 90% on eight of ten functions.
Cormac walks through the two paths developers have for on device AI: a skill harness built on Gemma 4 with a restaurant roulette demo running fully on device. Then Eloquent, a production transcription app built by chaining two sub billion parameter models together.
cc @osanseviero
Cormac Brick retweeted
Check out this video on how to run Gemma 4 locally on an iPhone!
It runs completely offline and handles long context, meaning no data plan, no API calls, and no monthly fees required.
Cormac Brick retweeted
Our first successful Gemma 4 Runtime in London with @swyx @patloeber @nick_kango @cormacb and others! 💎Great to go out for a run and talk about Gemma, agents, evals and more
Hello @memdotai 👋 just setting up my Twitter flow. Here's my validation code: TyWbWXsnd84F3Pb0Q68l
Cormac Brick retweeted
Do you like #AnimalCrossing
Do you like artificial intelligence 💻
Do you like workshops 🧠
acaiworkshop.com
Awesome (in the literal sense)...
Here's a ridiculous result from the @OpenAI GPT-2 paper (Table 13) that might get buried --- the model makes up an entire, coherent news article about TALKING UNICORNS, given only 2 sentences of context.
WHAT??!!
This is really cool project, congrats to Lucian and all involved -- battery life increase from 6 weeks to 1.5 years!
lnkd.in/gg5Ypz9 lnkd.in/gwwmaRv
We are hiring in Seattle to join the Vertex.ai crew that recently joined us through acquisition. Great opportunity to join a top class team working on one of the new frontiers of CS/ML. lnkd.in/gEaDYxZ
Cormac Brick retweeted
My colleague Raghu has just released "Quantizing deep convolutional networks for efficient inference" - arxiv.org/abs/1806.08342v1
This white paper covers practical quantization approaches for most common CNNs in @TensorFlow, I think it will be super useful! – at Salt Lake City, UT
Cormac Brick retweeted
It is starting to look like deep learning workflows of the future feature autotuned architectures running with autotuned compute schedules across arbitrary backends. I don't know if I should be excited or scared.
Cormac Brick retweeted
Intel and Microsoft Enable AI Inference at the Edge with Intel Movidius Vision Processing Units on Windows ML sco.lt/5kPStt
Cormac Brick retweeted
I'm on the steering committee of SysML, a new conference that targets work at the intersection of computer systems and machine learning. The inaugural event will be at Stanford, Feb. 15-16, 2018, and submissions are due January 5th. Consider submitting if you have relevant work! xitter.cf/edchi/status/942160617…
SysML is a new conference on systems and machine learning. Non-archival this year. The inaugural conference will take place Feb 15-16, 2018 in Stanford, CA. Consider submitting your work! sysml.cc/#submission #sysml2018