Ion Stoica
@istoica05
Followers
6K
Following
2
Media
2
Statuses
54
Professor at UC Berkeley, co-founder of Databricks, Anyscale, LMArena, Conviva.
Bay Area
Joined April 2015
🚀 End the GPU Cost Crisis Today!!! Headache with LLMs lock a whole GPU but leave capacity idle? Frustrated by your cluster's low utilization? We launch kvcached, the first library for elastic GPU sharing across LLMs. 🔗 https://t.co/3BC7B6s2EX 🧵👇 Why it matters:
9
53
189
🚀 SkyRL has day-zero support for OpenEnv!! This initial integration with OpenEnv highlights how easily new environments plug into SkyRL. Train your own LLM agents across containerized environments with simple, Gym-style APIs 🔥 👉 Check it out:
Excited to share OpenEnv: frontier-grade RL environments for the open-source community 🔥! https://t.co/KVeBMsxohL 🧩 Modular interfaces: a clean Gymnasium-style API (reset(), step(), state()) that plugs into any RL framework 🐳 Built for scale: run environments in containers
0
9
20
Deep dive into NYC’s political circus with: Joseph Borelli – fiery conservative ex-Councilman Tom Allon – veteran journalist on media & mayhem Sun, Nov 2 | 7–9 PM ET SHAKE IT OFF WITH MERT & LUCAS Live on AM970 radio and streaming everywhere!
0
3
31
🚀 We used AI to discover a new algorithm for LLM inference, achieving a 5.0x speedup in MoE load balancing over expert-written code. ✍️ Read the details in our blog post: https://t.co/sHVRqX6wDR 📄 Full paper: https://t.co/ex6AidUuwK 💻 Code: https://t.co/o2EVHmFMCl
0
8
36
🚀 AI is no longer just a "black box" for tuning systems. It's now a "white box" that rewrites core algorithms and outperforms human experts! We use AI-Driven Research for Systems (ADRS) frameworks to discover state-of-the-art solutions in under 12 hours for less than $20. This
adrs-ucb.notion.site
🗓️ Posted: October 17, 2025
0
7
26
Barbarians at The Gate: How AI is Upending Systems Research by @audreyccheng, @LynnLiu41887950, @melissapan, @istoica05, and the @ai4research_ucb team, https://t.co/b6vtMJN3Et This's first article of the The Next Horizon of System Intelligence blog series.
0
8
21
If you're running agents in production, consider taking this short survey from my research group! We're collaborating with IBM, Stanford, UIUC, Intesa Sanpaolo and others to better understand the challenges in building agents. It only takes 5 minutes:
agents-survey.github.io
A collaboration of over 20 researchers across UC Berkeley, Intesa Sanpaolo, IBM Research, UIUC, and Stanford working on industry-grade agentic AI systems.
7
28
130
@MarcJBrooker "It takes more experience, more insight, and more vision to choose problems than to optimize on them. It takes more taste to reject noise, and avoid following dead ends, than to follow the trend." Couldn't agree more!
1
2
7
The family unit is under attack! Stand with us as we fight the anti-family left!
0
9
157
Excited to share our new paper on AI-Driven Research for Systems. We show that AI can autonomously generate and verify novel solutions for classic systems performance problems, matching or exceeding human designs. A glimpse into how AI might transform not only systems, but the
🚀 Excited to release our new paper: “Barbarians at the Gate: How AI is Upending Systems Research” We show how AI-Driven Research for Systems (ADRS) can rediscover or outperform human-designed algorithms across cloud scheduling, MoE expert load balancing, LLM-SQL optimization,
5
33
178
Great to see an open source backend in the works for the Tinker API. If Tinker is going to power open science and open software, it shouldn’t depend on a single proprietary implementation.
The Tinker API recently released by Thinking Machines will have a big impact on how people think about post-training and inference systems. To allow more people to experiment with Tinker like systems and run it on their own hardware, we started SkyRL tx 🧸, an open source project
1
24
380
Introducing SkyRL tx 🧸, an open-source project to implement the Tinker API. The SkyRL team is excited about the Tinker API and the opportunities of using a single canonical interface that unifies training and inference. SkyRL tx lets you run a Tinker-like service locally today,
novasky-ai.notion.site
6
30
242
🚀 Introducing Sparse VideoGen2 (SVG2) — Pareto-frontier video generation acceleration with semantic-aware sparse attention! 🏆Spotlight paper accepted by #NeurIPS2025 ✅ Training-free & plug-and-play ✅ Up to 2.5× faster on HunyuanVideo, 1.9× faster on Wan 2.1 ✅ SOTA quality
16
58
259
We're entering our next phase of growth at @gambulls As we scale globally, we are connecting with strategic investors who share our vision for the next evolution of crypto gaming. If you / your fund has interest in becoming a strategic growth partner with Gambulls, our DMs are
1
21
61
Modern AI teams need hyperscalers & neoclouds, but legacy tools like SLURM can't keep up. @AbridgeHQ moved from SLURM to multi-cloud AI infra with @skypilot_org. ✅ 10x faster dev cycles ✅ SLURM-like convenience, K8s' reliability ✅ Scale on any infra https://t.co/n5XIEbEy9w
0
4
11
Interested in building and benchmarking deep research systems? Excited to introduce DeepScholar-Bench, a live benchmark for generative research synthesis, from our team at Stanford and Berkeley! 🏆Live Leaderboard https://t.co/gWuylXVlkJ 📚 Paper: https://t.co/BbtsoZHlSh 🛠️
1
41
174
🚀 Last week we hosted the vLLM Beijing Meetup with top players like Tencent @TencentHunyuan , Huawei @Huawei , ByteDance @ByteDanceOSS , Ant Group @AntGroup , Moonshot AI @Kimi_Moonshot & Xiaomi @XiaoMi_AI ! 💡 Discover how industry leaders are using vLLM to power
1
13
107
(1/n) 🚀 With FastVideo, you can now generate a 5-second video in 5 seconds on a single H200 GPU! Introducing FastWan series, a family of fast video generation models trained via a new recipe we term as “sparse distillation”, to speed up video denoising time by 70X! 🖥️ Live
10
99
422
Remarkable how far we've come. From fear mongering OS AI across VC, academia, AI labs, and politicians to full throated endorsement. Thank you to everyone who has taken a stand on this over the last couple of years. In no small way have you helped sway and save a nation.
18
61
396
Congratulations to my brilliant co-founder Philipp Moritz (@pcmoritz) and the legendary John Schulman, Sergey Levine, Pieter Abbeel, and Michael Jordan on their Test-of-Time Honorable Mention at ICML 2025 today! For creating TRPO. This was done during the previous wave of
1
13
146
As AI agents near real-world use, how do we know what they can actually do? Reliable benchmarks are critical but agentic benchmarks are broken! Example: WebArena marks "45+8 minutes" on a duration calculation task as correct (real answer: "63 minutes"). Other benchmarks
7
33
96
it's awake. the way you interact with the web, information, and services is being rewritten. introducing FlowithOS — the world's first operating system natively built for ai agents. self-evolving. memory-powered. lightning-fast. beyond any ai browser, it's the SMARTEST agentic
414
301
1K
🚀 Introducing DeepSWE 🤖: our fully open-sourced, SOTA software engineering agent trained purely with RL on top of Qwen3-32B. DeepSWE achieves 59% on SWEBench-Verified with test-time scaling (and 42.2% Pass@1), topping the SWEBench leaderboard for open-weight models. 💪DeepSWE
15
71
370
Taking a step towards building a modular RL framework with our SkyRL project.
✨Release: We upgraded SkyRL into a highly-modular, performant RL framework for training LLMs. We prioritized modularity—easily prototype new algorithms, environments, and training logic with minimal overhead. 🧵👇 Blog: https://t.co/jDvM95F0Bq Code: https://t.co/CWlKue79JH
5
14
70