charlie_ruan's profile picture. CS PhD Student @UCBerkeley @BerkeleySky | prev @CSDatCMU, @CornellCIS

Charlie Ruan

@charlie_ruan

CS PhD Student @UCBerkeley @BerkeleySky | prev @CSDatCMU, @CornellCIS

Charlie Ruan repostou

A shift from cloud to edge? We took a closer look at “Local LMs” (≤20B active parameters) and found that they are: - Surprisingly capable, with 3.1× improvement since 2023 - Increasingly efficient, with 5.3x improvement since 2023 This suggests a shift from mainframe inference…

Azaliamirh's tweet image. A shift from cloud to edge?
We took a closer look at “Local LMs” (≤20B active parameters) and found that they are:
- Surprisingly capable, with 3.1× improvement since 2023
- Increasingly efficient, with 5.3x improvement since 2023
This suggests a shift from mainframe inference…

Charlie Ruan repostou

Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands? The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):…

JonSaadFalcon's tweet image. Data centers dominate AI, but they're hitting physical limits. What if the future of AI isn't just bigger data centers, but local intelligence in our hands?

The viability of local AI depends on intelligence efficiency. To measure this, we propose intelligence per watt (IPW):…

Charlie Ruan repostou

Huge thanks to the Laude team for supporting SkyRL with the Slingshots program! Andy and the team at @LaudeInstitute have already been a big help to the project and OSS research in general

Meet Slingshots // One. This inaugural batch includes leading-edge researchers advancing the science and practice of AI - with benchmarks, frameworks, and agents that ship real impact into the world. We're honored to support research from: @alexgshaw @Mike_A_Merrill

LaudeInstitute's tweet image. Meet Slingshots // One. 

This inaugural batch includes leading-edge researchers advancing the science and practice of AI - with benchmarks, frameworks, and agents that ship real impact into the world. 

We're honored to support research from:

@alexgshaw @Mike_A_Merrill…


Charlie Ruan repostou

We are happy to release SkyRL tx 0.1 novasky-ai.notion.site/skyrl-tx-v010, an open source unified training and inference engine that supports the Tinker API. This release has many performance enhancements and also new features but most importantly RL training is now working end-to-end. If you…

pcmoritz's tweet image. We are happy to release SkyRL tx 0.1 novasky-ai.notion.site/skyrl-tx-v010, an open source unified training and inference engine that supports the Tinker API. This release has many performance enhancements and also new features but most importantly RL training is now working end-to-end. If you…

Charlie Ruan repostou

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-tx-v010

tyler_griggs_'s tweet image. 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-tx-v010

Charlie Ruan repostou

Please steal my AI research ideas. This is a list of research questions and concrete experiments I would love to see done, but don't have bandwidth to get to. If you are looking to break into AI research (e.g. as an undergraduate, or a software engineer in industry), these are…


Charlie Ruan repostou

☁️SkyRL now runs seamlessly with SkyPilot! Let @skypilot_org handle GPU provisioning and cluster setup, so you can focus on RL training with SkyRL. 🎯 Launch distributed RL jobs effortlessly ⚙️ Auto-provision GPUs across clouds 🤖 Train your LLM agents at scale Get started…

NovaSkyAI's tweet image. ☁️SkyRL now runs seamlessly with SkyPilot! 

Let @skypilot_org handle GPU provisioning and cluster setup, so you can focus on RL training with SkyRL.

🎯 Launch distributed RL jobs effortlessly
⚙️ Auto-provision GPUs across clouds
🤖 Train your LLM agents at scale

Get started…

Charlie Ruan repostou

Wrote a 1-year retrospective with @a1zhang on KernelBench and the journey toward automated GPU/CUDA kernel generations! Since my labmates (@anneouyang, @simran_s_arora, @_williamhu) and I first started working towards this vision around last year’s @GPU_mode hackathon, we have…

simonguozirui's tweet image. Wrote a 1-year retrospective with @a1zhang on KernelBench and the journey toward automated GPU/CUDA kernel generations!

Since my labmates (@anneouyang, @simran_s_arora, @_williamhu) and I first started working towards this vision around last year’s @GPU_mode hackathon, we have…

Charlie Ruan repostou

Together with the FlashInfer community, we built FlashInfer-Bench — a benchmark of real-world, AI system–driven GPU workloads — and, more importantly, an infrastructure and workflow to 0‑day ship AI‑generated kernels into production.

NVIDIAAIDev's tweet image. Together with the FlashInfer community, we built FlashInfer-Bench — a benchmark of real-world, AI system–driven GPU workloads — and, more importantly, an infrastructure and workflow to 0‑day ship AI‑generated kernels into production.

🚀Excited to launch FlashInfer Bench. We believe AI has the potential to help build LLM systems . To accelerate the path, we need an open schema for critical workloads and an AI-driven virtuous circle. First-class integration with FlashInfer, SGLang and vLLM support👉



Charlie Ruan repostou

🚀 End the GPU Cost Crisis Today!!! Headache with LLMs lock a whole GPU but leave capacity idle? Frustrated by your cluster's low utilization? We launch kvcached, the first library for elastic GPU sharing across LLMs. 🔗 github.com/ovg-project/kv… 🧵👇 Why it matters:

yifandotqiao's tweet image. 🚀 End the GPU Cost Crisis Today!!!

Headache with LLMs lock a whole GPU but leave capacity idle? Frustrated by your cluster's low utilization?

We launch kvcached, the first library for elastic GPU sharing across LLMs.
🔗 github.com/ovg-project/kv…
🧵👇 Why it matters:

Charlie Ruan repostou

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-tx-003


Charlie Ruan repostou

📢Excited to introduce Apache TVM FFI, an open ABI and FFI for ML systems, enabling compilers, libraries, DSLs, and frameworks to naturally interop with each other. Ship one library across pytorch, jax, cupy etc and runnable across python, c++, rust tvm.apache.org/2025/10/21/tvm…

tqchenml's tweet image. 📢Excited to introduce Apache TVM FFI, an open ABI and FFI for ML systems, enabling compilers, libraries, DSLs, and frameworks to naturally interop with each other. Ship one library across pytorch, jax, cupy etc and runnable across python, c++, rust tvm.apache.org/2025/10/21/tvm…

Charlie Ruan repostou

Live from the AI Infra Summit, co-located with #PyTorchCon — Tianqi Chen (@nvidia) explores how shared ML foundations can advance interoperability across compilers, libraries, DSLs, and frameworks, while unifying workloads across edge and cloud. 🔗 hubs.la/Q03PBnK00

PyTorch's tweet image. Live from the AI Infra Summit, co-located with #PyTorchCon — Tianqi Chen (@nvidia) explores how shared ML foundations can advance interoperability across compilers, libraries, DSLs, and frameworks, while unifying workloads across edge and cloud. 
🔗 hubs.la/Q03PBnK00…
PyTorch's tweet image. Live from the AI Infra Summit, co-located with #PyTorchCon — Tianqi Chen (@nvidia) explores how shared ML foundations can advance interoperability across compilers, libraries, DSLs, and frameworks, while unifying workloads across edge and cloud. 
🔗 hubs.la/Q03PBnK00…
PyTorch's tweet image. Live from the AI Infra Summit, co-located with #PyTorchCon — Tianqi Chen (@nvidia) explores how shared ML foundations can advance interoperability across compilers, libraries, DSLs, and frameworks, while unifying workloads across edge and cloud. 
🔗 hubs.la/Q03PBnK00…

Charlie Ruan repostou

🚀Excited to launch FlashInfer Bench. We believe AI has the potential to help build LLM systems . To accelerate the path, we need an open schema for critical workloads and an AI-driven virtuous circle. First-class integration with FlashInfer, SGLang and vLLM support👉

🤔 Can AI optimize the systems it runs on? 🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents: - Standardized signature for LLM serving kernels - Implement kernels with your preferred language - Benchmark them against real-world serving…

shanli_xing's tweet image. 🤔 Can AI optimize the systems it runs on?

🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents:

- Standardized signature for LLM serving kernels
- Implement kernels with your preferred language
- Benchmark them against real-world serving…


A step towards creating the virtuous cycle for AI systems 🔥

🤔 Can AI optimize the systems it runs on? 🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents: - Standardized signature for LLM serving kernels - Implement kernels with your preferred language - Benchmark them against real-world serving…

shanli_xing's tweet image. 🤔 Can AI optimize the systems it runs on?

🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents:

- Standardized signature for LLM serving kernels
- Implement kernels with your preferred language
- Benchmark them against real-world serving…


Charlie Ruan repostou

Check out FlashInfer-Bench, the integrated ecosystem for agent-generated solutions in AI systems.

🤔 Can AI optimize the systems it runs on? 🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents: - Standardized signature for LLM serving kernels - Implement kernels with your preferred language - Benchmark them against real-world serving…

shanli_xing's tweet image. 🤔 Can AI optimize the systems it runs on?

🚀 Introducing FlashInfer-Bench, a workflow that makes AI systems self-improving with agents:

- Standardized signature for LLM serving kernels
- Implement kernels with your preferred language
- Benchmark them against real-world serving…


Charlie Ruan repostou

SkyRL v0.2.0 is here! With 22 contributors (including 11 new contributors!), this release holds many updates like strong MoE support with Megatron, LoRA support, standardized inference on the OpenAI API, new integrations, and many many more. The code: github.com/NovaSky-AI/Sky…

NovaSkyAI's tweet image. SkyRL v0.2.0 is here! 

With 22 contributors (including 11 new contributors!), this release holds many updates like strong MoE support with Megatron, LoRA support, standardized inference on the OpenAI API, new integrations, and many many more.

The code: github.com/NovaSky-AI/Sky…

Charlie Ruan repostou

We are happy to release SkyRL tx 0.0.2, an open source library that implements a backend for the Thinking Machine Tinker API and allows people to set up their own Tinker-like service running on their own hardware. There is lots of new features and it is exciting to see the first…

pcmoritz's tweet image. We are happy to release SkyRL tx 0.0.2, an open source library that implements a backend for the Thinking Machine Tinker API and allows people to set up their own Tinker-like service running on their own hardware. There is lots of new features and it is exciting to see the first…

Charlie Ruan repostou

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-tx-v002 Code: github.com/NovaSky-AI/Sky…


Charlie Ruan repostou

SkyRL just crossed 1000 Github stars! Thank you to all the wonderful contributors and users building this project together 🥳 Check it out: github.com/NovaSky-AI/Sky…

NovaSkyAI's tweet image. SkyRL just crossed 1000 Github stars! Thank you to all the wonderful contributors and users building this project together 🥳

Check it out: github.com/NovaSky-AI/Sky…

United States Tendências

Loading...

Something went wrong.


Something went wrong.