English
Philipp Moritz
Report

Philipp Moritz✓

@pcmoritz

Co-founder and CTO at @anyscalecompute. Co-creator of @raydistributed. Interested in ML, AI, computing.

  • San Francisco
  • Joined
8 Following1.2K Followers128 Posts
  1. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @charlie_ruan: 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
    Datadog, Inc. @datadoghq
    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:
    01207
  2. Datadog, Inc.✓@datadoghq
    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:
    Download
    256633452.1K
  3. Philipp Moritz✓@pcmoritz
    Very happy to announce the release of Ray Sandboxes, developed with @a_sykim and his team at Google. It makes it easy to scale up your sandboxes with Ray, isolated by gVisor. It is fully open-source, check it out at Would love to get your feedback and contributions.
    Download
    321827.4K
  4. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @robertnishihara: 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
    Anyscale @anyscalecompute
    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.
    0401
  5. Anyscale✓@anyscalecompute
    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.
    Download
    01133.6K
  6. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @sumanthrh: 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 🧵
    02007
  7. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @raydistributed: 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
    Microsoft AI @MicrosoftAI
    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
    010016K
  8. Microsoft AI✓@MicrosoftAI
    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
    Download
    256980958.4K
  9. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @nithinch10: 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:
    01104.6K
  10. Philipp Moritz✓@pcmoritz
    We just merged a clean Qwen 3.5 implementation for SkyRL's Jax backend: Currently only for dense models, but should be easy to adapt to MoE models, contributions welcome! Also if anybody wants to contribute chunkwise training for the gated delta net or layer stacking for the model, it would be welcome!
    17464.2K
  11. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @jeffreyycwang: 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 🧵
    027013.8K
  12. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @charlie_ruan: 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: 🧵
    045035.8K
  13. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @tinkerapi: 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!
    Tyler Griggs @tyler_griggs_
    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: 🧵
    016010.6K
  14. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @tyler_griggs_: 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: 🧵
    053059.9K
  15. Philipp Moritz✓@pcmoritz
    We just released the full SkyRL + Tinker integration: This is the evolution of what we have been working on with SkyRL tx and now also supports the SkyRL train backend (fsdp and megatron) which could previously only be used through Python APIs. I'm excited about the standardization the Tinker API will bring to the ecosystem and hopefully having a great open-source implementation will accelerate the adoption!
    Download
    19442.2K
  16. Philipp Moritz✓@pcmoritz
    We are excited to announce the release of SkyRL tx 0.3 our MultiLoRA native inference and training engine that exposes the Tinker API. A lot has happened since the last release, in terms of big features we implemented expert parallelism, the DeepseekV3 model architecture (e.g. GLM 4.7 Flash) and a number of features to support longer context! Also, there are lots of smaller improvements and a few small bug fixes.
    Download
    776812.7K
  17. Philipp Moritz✓@pcmoritz
    Thanks a lot for the call-out @tinkerapi For anybody who is interested, we have made a bunch more releases since 0.1.0 came out, they are listed in (and 0.3.0 with expert parallelism, a bunch of long context optimizations, and DeepSeekV3 is coming very soon).
    Tinker @tinkerapi
    SkyRL-tx by @BerkeleySky is an open-source backend that implements the Tinker API itself, letting users train on their own hardware. It supports end-to-end RL, faster sampling, and gradient checkpointing — giving users flexibility and control.
    0191.1K
  18. Tinker✓@tinkerapi
    Posts @tinkerapi
    SkyRL-tx by @BerkeleySky is an open-source backend that implements the Tinker API itself, letting users train on their own hardware. It supports end-to-end RL, faster sampling, and gradient checkpointing — giving users flexibility and control.
    13262.8K
  19. Philipp Moritz✓@pcmoritz
    If anybody is looking for a fun weekend project and is interested in kernels and how ragged_dot can be used to implement MultiLoRA for training and inference as well as MoE models, check out Contributions very welcome, happy to discuss more in the issue!
    13252.6K
  20. Philipp Moritz✓@pcmoritz
    Philipp Moritz
    RT @tyler_griggs_: 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!
    0402.8K
  21. Philipp Moritz✓@pcmoritz
    Happy new year! We are excited to announce SkyRL tx 0.2.1, see Some highlights of the release include FSDP and multi-node support, Llama 3 model support, custom loss functions, a number of performance improvements and also lots of small fixes that implement more functionality of the Tinker API. The blog post also includes a performance comparison with the Tinker Service! Enjoy the release and happy hacking!
    Download
    1157911.3K
  22. Philipp Moritz✓@pcmoritz
    We are happy to announce SkyRL tx 0.2, see our blog post It comes with lots of performance improvements, all parts of the execution now use jax jit, so there is very little overhead. Now is probably the best time to try it out if you haven't already 🧸
    Download
    283912.8K
  24. Show more posts