Nan Jiang

building fun stuff @modal

[Nan Jiang @nanjiangwill]

c you there!

[Modal @modal]

We're bringing together our friends and community to celebrate our Series C.

Join us at Noguchi's Sunken Garden in NYC on June 16th or at the Legion of Honor in SF on June 25th.

Invites are limited, apply here: https://t.co/B4h0C7Wq0Q

[Nan Jiang @nanjiangwill]

@justintchiu strands is an agentic scaffold(like agent loop) from aws. and strands-sglang is the tito version of it, the code itself is very minimal.

i will say it is not as clean as renderer to serve the purpose of tito only

[Nan Jiang @nanjiangwill]

@justintchiu efficiency wise?

[Luke J. Huang @whatthelukh]

New blog! Is frontier asynchronous RL solved?

The blog covers Async RL theory and infrastructure, surveying 8 open-weight frontier labs for the algorithmic techniques and systems fixes to handle train-inference mismatch. Also answered: why do current methods still fail at high policy lag? Which methods scale with horizon and compute?

[Nan Jiang @nanjiangwill]

love the design so much

[Feather @feather___co]

Introducing Feather - A self organizing inbox!

Try it out at https://t.co/Z5N2OG8loZ. We'd love to know what you think 🪶

[slime @slime_framework]

🚀 slime v0.3.0 is out!

This release is a major step toward agent-first RL.

We turned slime’s existing multi-turn / agentic capabilities into a more coherent foundation:

- slime/agent with reusable sandbox-agent components
- OpenAI / Anthropic-compatible adapters
- black-box coding-agent RL example
- variable global batch-size training
- fully async training as a first-class path
- lower host-memory usage for more flexible rollout-inference setups
- PPO refactor with actor-critic colocation
- delta weight sync, FlashQLA for Qwen GDN, --save-hf, and more CI coverage

slime is moving closer to a practical open-source framework for large-scale agentic RL.

Release note:
https://t.co/e1ONv8Q4aW

[Nan Jiang @nanjiangwill]

@_dcw02 me with 1 commit to the modal monorepo for registering prbot

[Nan Jiang @nanjiangwill]

@hsubbaraj @peywalt @modal you too my goat

[Nan Jiang @nanjiangwill]

@charles_irl @peywalt @modal NAN!

[Nan Jiang @nanjiangwill]

@peywalt @modal love the meme as always haha

[Nan Jiang @nanjiangwill]

@zhuohaolix @modal sglang🧑‍🍳

[Nan Jiang @nanjiangwill]

At @modal, we're working to make sure OSS RL frameworks have all the techniques necessary to train frontier open-weights models.

Delta compression is key, but the job's not done. There are still lots of open problems around weight sync, auto-scaling, & cross-cluster training.

My DMs are open!

[slime @slime_framework]

@FireworksAI_HQ + @cursor_ai highlighted why delta-compressed weight sync matters for RL at frontier scale.

slime brings this capability to OSS: lossless delta sync for Megatron ↔ SGLang disaggregation — ship deltas, not full checkpoints.

This is another step toward a fully open-source stack where rollout/inference and training are truly decoupled and deployed separately.

PR: https://t.co/OoFR2VJVn1

[Nan Jiang @nanjiangwill]

@emilyhanyf @waltergoat @modal 🧑‍🍳🧑‍🍳

[Nan Jiang @nanjiangwill]

@FutbolmeAI @modal slime patches sglang here https://t.co/zaUL3LSJHN

and the one for sglang https://t.co/hCfb1TIO0H

[Nan Jiang @nanjiangwill]

@iamashtonchew @modal ??????

[Nan Jiang @nanjiangwill]

Huge thanks to the @slime_framework community for making an amazing, battle-tested RL framework!

I think we are well-positioned at Modal to help users deploy slime. On our infrastructure, train/inference disaggregation can pair naturally with elastic scaling, so rollout capacity is neither wasted nor bottlenecked.

[Nan Jiang @nanjiangwill]

@srush_nlp joined a while ago! mostly in nyc/sf these days and doing some RL work

[Nan Jiang @nanjiangwill]

omg

[Sasha Rush @srush_nlp]

Big fan (and neighbor) of Modal. Seems like a great group to work with as well.

[Erik Bernhardsson @bernhardsson]

Today we're announcing our Series C funding: $355M at a $4.65B valuation, led by some great investors @generalcatalyst and @Redpoint.

We've had insane growth in the last year, but we're still very early. So proud of the team and what we have built so far!