Anyscale (@anyscalecompute) header
Anyscale (@anyscalecompute) profile picture

The best way to run @raydistributed, the distributed compute framework for scaling AI workloads.

Joined September 2019
Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)Photo by Anyscale (@anyscalecompute)
Anyscale is coming to Thailand for the first time 🇹🇭 Join us on Thu Dec 3 at Siam Inference Meetup #1 in Bangkok Edward + Pawarit will show how Ray powers the AI model lifecycle: data curation → post-training → serving with vLLM 🎟️ na2.hubs.ly/H095LWb0
1
2
1
11
872
Had a lot of fun at the Mercor x Harbor x SkyRL meetup. Thanks @mercor for hosting!
Completely packed RL & data meetup last night! - @TaoTianhua spoke about RL at @mercor with SkyRL - @charlie_ruan shared day-zero model support, the latest SkyRL features - @avigyabasnet talked about 1M-token context training work from @anyscalecompute and @LilaSciences - @xinyzng spoke about native @raydistributed sandboxes - @yaoma_ai shared @coinbase’s work on building custom specialist models - @alexgshaw talked about RL environments and @harborframework
1
2
33
1,578
Impressive talk at KubeCon on how @hark_labs builds computer-use agents and multi-modal models. @kaihsunchen and Hao Jiang explain how they use @raydistributed & @kubernetesio together for - data processing - training - evals - inference All across autoscaling, heterogeneous clusters. youtube.com/watch?v=06JNFaNF…
2
3
1
12
2,204
Anyscale retweeted
SkyRL is everywhere.
Completely packed RL & data meetup last night! - @TaoTianhua spoke about RL at @mercor with SkyRL - @charlie_ruan shared day-zero model support, the latest SkyRL features - @avigyabasnet talked about 1M-token context training work from @anyscalecompute and @LilaSciences - @xinyzng spoke about native @raydistributed sandboxes - @yaoma_ai shared @coinbase’s work on building custom specialist models - @alexgshaw talked about RL environments and @harborframework
1
8
1,012
Completely packed RL & data meetup last night! - @TaoTianhua spoke about RL at @mercor with SkyRL - @charlie_ruan shared day-zero model support, the latest SkyRL features - @avigyabasnet talked about 1M-token context training work from @anyscalecompute and @LilaSciences - @xinyzng spoke about native @raydistributed sandboxes - @yaoma_ai shared @coinbase’s work on building custom specialist models - @alexgshaw talked about RL environments and @harborframework
6
3
20
4,413
Last chance to sign up for next week's webinar! Don't miss the opportunity to learn about reinforcement learning for post-training: - How the underlying algorithms work (e.g., RLVR with GRPO) - Recent research advances (on-policy distillation (OPD), multi-teacher on-policy distillation (MOPD)) - Details of post-training a terminal agent (building evals, building custom environments, RL systems) - SkyRL deep dive (async RL, performance monitoring, tuning for RL rollouts) Register: na2.hubs.ly/H08TZfT0
1
8
529
Here's the keynote @istoica05 gave at PyTorch Conference on some of the history of Ray. youtube.com/watch?v=HXxV3GcM…
1
4
408
JEPA world models plan by scoring hundreds of candidate action sequences. On a single onboard GPU, that took us 16 s per action. Fanning the search out with Ray Serve across 8x A100s: 2.8 s. That’s 5.7x faster. Blog + runnable example: na2.hubs.ly/H08ZhyJ0
2
1
3
429
Anyscale is at #KubeCon in Salt Lake City this week. Find us at booth #P317, join KubeRay 101 on Nov 11, and catch Rueian Huang on The Scheduling Stack panel on Nov 12. na2.hubs.ly/H08TtmM0
1
4
453
📍Nov 17-20 we're at Microsoft Ignite, Moscone SF. Booth 5389L. The next wave of foundation models is coming from enterprises. Every company needs at least one FM it controls: open model, post-trained on your data, on your infra. Session Nov 18 (THR900). Learn more: na2.hubs.ly/H08V4YK0
1
1
4
568
Using Ray on Kubernetes? Try a streamlined approach to run observability and development with KubeRay Connect. New accounts get $500 in Anyscale Platform credits (limited time offer) to test out KubeRay Connect today! 👉 Claim your $500 credits
1
1
2
425
Big news at KubeCon Americas. KubeRay is joining the @CloudNativeFdn Keep your KubeRay stack and add the Anyscale Control Plane in minutes. Find us at #KubeCon booth #P317.  na2.hubs.ly/H08TY0t0
2
5
22
4,904
Physical AI Night is back on Nov 17 in SF! We’re teaming up with @Foxglove & @nebiusai to hear from leaders at @BedrockRobotics, @DexterityInc, @wayve_ai & @ThirdWaveAi on the frontier of robotics and autonomy. Save your seat: na2.hubs.ly/H08Qb7p0
3
1
6
501
For post-training AI for science, a genome doesn't fit in a 16k context window. So we went to 1M. To solve this, the SkyRL team at Anyscale worked with @LilaSciences to post-train GLM-5.3-Flash at 1M tokens per sequence on 64 B200 GPUs, using a fully open-source stack. Learn more: na2.hubs.ly/H08Q9vw0
4
3
1
17
2,418
In this session, @erictang000, Software Engineer at Anyscale, will walk through: - Intro to LLM post-training - Intro to RLVR (with GRPO) - Recent development of LLM post-training:     - On-policy distillation (OPD) and Multi-teacher On-policy distillation (MOPD) - Case study: Post-training a terminal agent     - Building evals     - Building custom environments     - RL systems - Demo walkthrough     - Intro to SkyRL     - Full Async RL with SkyRL     - Performance monitoring and tuning for RL rollouts Register: na2.hubs.ly/H08wNDx0
1
5
463
Lots of great topics. This covers - SkyRL at Mercor - What’s new in SkyRL - 1M-context training - Token-in token-out - Ray Sandboxes - Harbor - Terminal-Bench
7
111
10,839