Co-founder and CTO at @anyscalecompute. Co-creator of @raydistributed. Interested in ML, AI, computing.
San Francisco
Joined April 2017
- Tweets128
- Following8
- Followers1.2K
- Likes1.2K
Philipp Moritz retweeted
Datadog post-trained GLM-5.3 Flash via RL on real-incident sims. Matches frontier SRE performance at much lower cost.
Their RL stack is built on top of SkyRL! Check out the technical report web-assets.dd-static.net/425…
Meet Scout 1.0, our first AI model built for investigating production incidents.
Scout matches frontier-model investigation quality at a fraction of the cost, which makes it practical to investigate more issues, earlier.
We trained Scout on realistic simulations built from real-world incidents and production telemetry, using reinforcement learning to reward accurate root causes backed by evidence.
Learn more and sign up for the preview: bit.ly/3TJknGO
Philipp Moritz retweeted
This will be our best Ray Summit yet. Compared with last year, we're seeing so many more talks on
- AI for science
- Physical AI
- Reinforcement learning
Extremely excited to hear from so many companies including @inferact @LilaSciences @periodiclabs @BedrockRobotics @mimicrobotics @mercor @ElorianAI @_inception_ai @torc_robotics @LumaLabsAI @radixark @xiaohongshu @GoogleDeepMind @MiniMax_AI @ExaAILabs
7 days to Ray Summit 2026.
The teams running Ray in production, live in one room. Keynotes, 80+ sessions, Training Day, and the @vllm_project Conference.
Aug 24–26, San Francisco. Passes are nearly gone.
na2.hubs.ly/H07dx7S0
Philipp Moritz retweeted
Excited to announce the release of SkyRL v0.3.0!
SkyRL’s focus in this release revolves around three major themes:
1. Support for large scale, async RL
2. Improving SkyRL’s Tinker API for self-hosting Tinker servers
3. Providing a unified library for SFT and RL
Some highlights 🧵
Philipp Moritz retweeted
Congratulations to the Microsoft AI team on MAI-Thinking-1! Exciting to see Ray used in multiple parts of frontier-model development.
- Fast pre-training recovery via in-job restarts with hot standbys
- Async RL orchestration (managing learners, inference servers, rollout workers, and routers, each with distinct placement and fault-tolerance needs)
- A two-pool Ray cluster for building and grading SWE environments on 30K CPU cores
MAI-Thinking-1 is our first in-house reasoning model developed from scratch that is competitive with models of similar size on STEM reasoning and coding tasks.
35B active/1T total MOE.
💻Coding: 52.8% on SWE Bench Pro competitive with Opus 4.6
🧐 Reasoning: 97% on AIME 25
🤝Preferred to Sonnet 4.6 on blind side-by-side tests
ALT Table comparing MAI‑Thinking‑1 with other models on STEM and coding benchmarks, showing performance scores across multiple tests.
RT @charlie_ruan: Excited to have supported @trajectorylabs with the SkyRL team over the past month, bringing training onto their own clust…
This quoted post is unavailable.
Philipp Moritz retweeted
SkyRL now supports end-to-end vision-language post-training, from SFT to agentic RL, and adds vision model support to SkyRL’s Tinker interface! Existing multimodal cookbooks, e.g. VLM classification, work out of the box:
Philipp Moritz retweeted
We just published how Ray Data LLM unlocks up to 2x higher throughput vs plain vLLM offline inference by fixing orchestration bottlenecks.
Offline batch inference is critical for synthetic data, evals, indexing – but vLLM alone doesn’t fully scale.
We compare:
• Plain vLLM
• Ray Data + vLLM offline engine
• Ray Data LLM 🧵
Philipp Moritz retweeted
Releasing the official SkyRL + Harbor integration: a standardized way to train terminal-use agents with RL.
From the creators of Terminal-Bench, Harbor is a widely adopted framework for evaluating terminal-use agents on any task expressible as a Dockerfile + instruction + test script.
This integration extends it: the same tasks you evaluate on, you can now RL-train on.
Blog: novasky-ai.notion.site/skyrl…
🧵
Philipp Moritz retweeted
You can now access SkyRL's backends for distributed training and inference with Tinker scripts so you can take advantage of Tinker's separation of infrastructure from training on your own hardware.
Exciting work from Tyler, @pcmoritz, and the team!
SkyRL now implements the Tinker API.
Now, training scripts written for Tinker can run on your own GPUs with zero code changes using SkyRL's FSDP2, Megatron, and vLLM backends.
Blog: novasky-ai.notion.site/skyrl…
🧵
Philipp Moritz retweeted
SkyRL now implements the Tinker API.
Now, training scripts written for Tinker can run on your own GPUs with zero code changes using SkyRL's FSDP2, Megatron, and vLLM backends.
Blog: novasky-ai.notion.site/skyrl…
🧵
Philipp Moritz retweeted
We just pushed one of the biggest updates yet SkyRL tx (an OSS Tinker backend) including FSDP and multi-node support, custom loss functions, and Llama 3.
We also ran some comparisons to @thinkymachines Tinker service to validate tx. Check it out!
novasky-ai.notion.site/skyrl…
Philipp Moritz retweeted
SkyRL tx is now bumped to v0.1, which adds support for running @thinkymachines Tinker Cookbook RL loops unmodified out of the box!
We'll be talking more about tx at Ray Summit tomorrow at 4pm at the Ray Summit, please join if you're around
novasky-ai.notion.site/skyrl…
Philipp Moritz retweeted
Cursor just released a frontier coding model with 4x faster generation. They will be speaking at Ray Summit about their journey building a frontier coding model.
- Training on 1000s of GPUs
- Scaling 100,000s of sandboxed coding environments
- Custom training infrastructure with PyTorch and Ray
- Custom MoE kernels, expert parallelism, hybrid sharded data parallelism
Philipp Moritz retweeted
Super excited for @raydistributed to join the PyTorch foundation! Daily downloads of Ray have grown nearly 10x over the past year (with the explosion of generative AI, reasoning models, RL, agents, and multimodal data). I'm very excited about growing the open source developer community around Ray.
We’re excited to welcome Ray to the PyTorch Foundation 👋 @raydistributed is an open source distributed computing framework for #AI workloads, including data processing, model training and inference at scale. By contributing Ray to the @PyTorch Foundation, @anyscalecompute reinforces its commitment to open governance and long-term sustainability for Ray and open source AI. ➡️ Read the announcement: hubs.la/Q03PyGP00 #PyTorchCon
Philipp Moritz retweeted
SkyRL tx just hit v0.0.3, adding full MoE support, better checkpointing, and a first stab at implementing the sampling interface. Very close to a complete RL loop on a locally-hosted @thinkymachines Tinker API server!
Blog: novasky-ai.notion.site/skyrl…
Philipp Moritz retweeted
SkyRL tx is our project to implement an open backend for the @thinkymachines Tinker API, and with version v0.0.2 it's ready to actually train some (multi-)LoRA models!
Blog: novasky-ai.notion.site/skyrl…
Code: github.com/NovaSky-AI/SkyRL/…
Philipp Moritz retweeted
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, but the project is early and we want to collaborate with you all!
Blog: novasky-ai.notion.site/skyrl…
Code: github.com/NovaSky-AI/SkyRL/…
Philipp Moritz retweeted
Scaling agentic simulations is hard, so in collaboration with @anyscalecompute we wrote up our experience using Ray for agent sims—featuring an end-to-end RL example with SkyRL!
Check it out here: anyscale.com/blog/massively-…
Philipp Moritz retweeted
Super excited to have @anyscalecompute use mini-swe-agent for their large scale runs!
w/ @KLieret @_carlosejimenez @jyangballin
