| 1. | | vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep (vllm.ai) |
| 147 points by robertnishihara 10 days ago | past | 54 comments |
|
| 2. | | Massively Parallel Agentic Simulations with Ray (anyscale.com) |
| 2 points by robertnishihara 4 months ago | past |
|
| 3. | | Deploy DeepSeek‑R1 with VLLM and Ray Serve on Kubernetes (anyscale.com) |
| 1 point by robertnishihara 5 months ago | past |
|
| 4. | | An Open Source Stack for AI Compute: Kubernetes and Ray and PyTorch and VLLM (anyscale.com) |
| 1 point by robertnishihara 5 months ago | past |
|
| 5. | | Native LLM APIs in Ray Data and Ray Serve (anyscale.com) |
| 2 points by robertnishihara 6 months ago | past |
|
| 6. | | Joins and Hash-Shuffle in Ray Data (anyscale.com) |
| 3 points by robertnishihara 6 months ago | past |
|
| 7. | | AsyncFlow: An Asynchronous Streaming RL Framework for LLM Post-Training (arxiv.org) |
| 4 points by robertnishihara 6 months ago | past |
|
| 8. | | Open Source RL Libraries for LLMs (anyscale.com) |
| 1 point by robertnishihara 6 months ago | past |
|
| 9. | | Large-Scale Deployment of Ray in Tencent's Weixin AI Infrastructure (anyscale.com) |
| 2 points by robertnishihara 6 months ago | past |
|
| 10. | | Uv and Ray: Pain-Free Python Dependencies in Clusters (anyscale.com) |
| 44 points by robertnishihara 7 months ago | past | 10 comments |
|
| 11. | | Roll: Reinforcement Learning Optimization for Large-Scale Learning (github.com/alibaba) |
| 1 point by robertnishihara 7 months ago | past |
|
| 12. | | An Open Source Stack for AI Compute: Kubernetes and Ray and PyTorch and VLLM (anyscale.com) |
| 1 point by robertnishihara 7 months ago | past |
|
| 13. | | Uv and Ray: Pain-Free Python Dependencies in Clusters (anyscale.com) |
| 1 point by robertnishihara 10 months ago | past |
|
| 14. | | Ray Batch Inference at Pinterest (Part 3) (medium.com/pinterest-engineering) |
| 1 point by robertnishihara on Oct 16, 2024 | past |
|
| 15. | | Direct Preference Optimization with Synthetic Data on Anyscale (anyscale.com) |
| 1 point by robertnishihara on Aug 21, 2024 | past |
|
| 16. | | Building an LLM Router for High-Quality and Cost-Effective Responses (anyscale.com) |
| 1 point by robertnishihara on July 2, 2024 | past |
|
| 17. | | Ray Infrastructure at Pinterest (medium.com/pinterest-engineering) |
| 1 point by robertnishihara on June 18, 2024 | past |
|
| 18. | | Lessons from training a Stable Diffusion model on 2B images (anyscale.com) |
| 5 points by robertnishihara on May 11, 2024 | past |
|
| 19. | | Canva Built a Modern AI Platform Using Anyscale (anyscale.com) |
| 2 points by robertnishihara on April 3, 2024 | past |
|
| 20. | | Building RAG-Based LLM Applications for Production (anyscale.com) |
| 2 points by robertnishihara on Feb 14, 2024 | past |
|
| 21. | | Fine-tuning LLMs for longer context and better RAG systems (anyscale.com) |
| 1 point by robertnishihara on Feb 13, 2024 | past |
|
| 22. | | Two-day hands-on RAG Bootcamp for developers (twitter.com/martin_casado) |
| 2 points by robertnishihara on Jan 31, 2024 | past |
|
| 23. | | RAG at Scale: 10x Cheaper Embedding Computations with Anyscale and Pinecone (anyscale.com) |
| 1 point by robertnishihara on Jan 16, 2024 | past |
|
| 24. | | Comparing LLM Performance: Introducing the Open Source Leaderboard for LLM APIs (anyscale.com) |
| 2 points by robertnishihara on Dec 21, 2023 | past |
|
| 25. | | LLMPerf Leaderboard (github.com/ray-project) |
| 5 points by robertnishihara on Dec 21, 2023 | past |
|
| 26. | | Anyscale Endpoints: JSON Mode and Function Calling Features (anyscale.com) |
| 2 points by robertnishihara on Dec 14, 2023 | past |
|
| 27. | | LLM summarization: A case study of human, Llama-2, & GPT-4 summarization quality (anyscale.com) |
| 1 point by robertnishihara on Nov 10, 2023 | past |
|
| 28. | | Reproducible Performance Metrics for LLM Inference (anyscale.com) |
| 2 points by robertnishihara on Nov 2, 2023 | past |
|
| 29. | | Building Rag-Based LLM Applications for Production (anyscale.com) |
| 3 points by robertnishihara on Oct 25, 2023 | past |
|
| 30. | | Anyscale Endpoints: LLM inference and fine-tuning (anyscale.com) |
| 1 point by robertnishihara on Oct 25, 2023 | past |
|
|
| More |
