Sumanth Hegde

@sumanthrh

Post-training @anyscalecompute. Prev - @UCSanDiego, @C3_AI, @iitmadras. Machine Learning and Systems. Intensity is all you need.

San Francisco

github.com/SumanthRH

Replies Reposts Media

已置顶
Sumanth Hegde
@sumanthrh
7月17日
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
12
Sumanth Hegde
@sumanthrh
9月2日
So glad to see this out! @charlie_ruan put in an ungodly amount of effort firefighting issues during training. This is one of the first E2E recipes for training 300B+ parameter MoE models on SkyRL. And probably one of the few in open source. Lots more to come :)
Edward Hu
@edwardjhu
9月1日
How does one RL post-train a 397B model for long-horizon knowledge work? 👩‍💼 We share every step we took to bring Qwen 3.5 397B from 16.1% Pass@1 to 27.3% on APEX-Agents using DPPO, including final models weights and the full training script🚀 This is the first of many works from
1
Sumanth Hegde
@sumanthrh
8月25日
Excited to share our work on large-scale sharded weight transfer! We’ve implemented a native sharded weight transfer engine in vLLM and SkyRL using Ray Direct Transfer (RDT) + NIXL. We’re able to achieve weight transfer for Kimi K2 (1T params) in BF16 in 7.53 seconds on 48
Aaron Hao
3
Sumanth Hegde
@sumanthrh
8月4日
Join us for the first-ever SkyRL Meetup! It's been a year since we released the SkyRL library. SkyRL now has 2k+ GitHub stars and a growing user base in academia and industry, including researchers from Stanford, CMU, UC Berkeley, Microsoft AI, Datadog, and more. We're hosting
Sumanth Hegde
@sumanthrh
5月30日
This is a special release. @j316chuck and team have been working closely with us in designing multi-LoRA training with SkyRL. @pcmoritz @tyler_griggs_ realized the value of the Tinker API a while back and led the Tinker server effort in SkyRL few months back. However we only
Chuck Tang
@j316chuck
5月30日
Had such a blast working with @erictang000 , @charlie_ruan, @sumanthhegde, and @pcmoritz on enabling multi-LoRA RL training in SkyRL! We observed ~3x higher experiments throughput in comparison to running experiments in the traditional single-tenant fashion. One of my favorite
5