| 1. | | Context Engineering for AI Agents: Lessons (manus.im) |
| 120 points by helloericsf 3 months ago | past | 4 comments |
|
| 2. | | Context Engineering for AI Agents: Lessons (manus.im) |
| 3 points by helloericsf 5 months ago | past |
|
| 3. | | Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model (huggingface.co) |
| 6 points by helloericsf 6 months ago | past |
|
| 4. | | kit - Code Intelligence Toolkit (github.com/cased) |
| 1 point by helloericsf 7 months ago | past |
|
| 5. | | DeepSeek Open Source Optimized Parallelism Strategies, 3 repos (github.com/deepseek-ai) |
| 103 points by helloericsf 10 months ago | past | 8 comments |
|
| 6. | | DeepSeek Open Source DeepGEMM – FP8 GEMM Library(300 lines for 1350+ FP8 TFLOPS) (twitter.com/deepseek_ai) |
| 4 points by helloericsf 10 months ago | past | 1 comment |
|
| 7. | | Alibaba Open Source Large-Scale Video Generative Models: Wan2.1 (twitter.com/_akhaliq) |
| 8 points by helloericsf 10 months ago | past | 2 comments |
|
| 8. | | DeepSeek open source DeepEP – library for MoE training and Inference (github.com/deepseek-ai) |
| 536 points by helloericsf 10 months ago | past | 71 comments |
|
| 9. | | DeepSeek Open Source FlashMLA – MLA Decoding Kernel for Hopper GPUs (github.com/deepseek-ai) |
| 441 points by helloericsf 10 months ago | past | 108 comments |
|
| 10. | | New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarks (twitter.com/justinlin610) |
| 3 points by helloericsf 11 months ago | past | 2 comments |
|
| 11. | | Longest context up to 4M, MiniMax-01 hybrid 456B Open source model (github.com/minimax-ai) |
| 19 points by helloericsf 11 months ago | past | 1 comment |
|
| 12. | | DeepSeek v3 beats Claude sonnet 3.5 and way cheaper (huggingface.co) |
| 48 points by helloericsf on Dec 26, 2024 | past | 9 comments |
|
| 13. | | NeurIPS and Dr. Picard released statement for singling out Chinese scholars (twitter.com/neuripsconf) |
| 2 points by helloericsf on Dec 16, 2024 | past | 2 comments |
|
| 14. | | Tencent Hunyuan-Large (github.com/tencent) |
| 148 points by helloericsf on Nov 5, 2024 | past | 103 comments |
|
| 15. | | Chinese AI Community: open-source Heatmap (huggingface.co) |
| 1 point by helloericsf on July 31, 2024 | past | 1 comment |
|
| 16. | | Poolside is raising $400M+ at a $2B valuation to build a coding co-pilot (techcrunch.com) |
| 3 points by helloericsf on June 20, 2024 | past | 1 comment |
|
| 17. | | Is LMDeploy the Ultimate Solution? Why It Outshines VLLM, TRT-LLM, TGI, and MLC (bentoml.com) |
| 16 points by helloericsf on June 20, 2024 | past | 8 comments |
|
| 18. | | 21.2× faster than llama.cpp? plus 40% memory usage reduction (arxiv.org) |
| 43 points by helloericsf on June 12, 2024 | past | 14 comments |
|
| 19. | | Databricks acquires Tabular, Snowflake fork Iceberg? (datagravity.dev) |
| 2 points by helloericsf on June 4, 2024 | past | 3 comments |
|
| 20. | | New Yi 1.5 models under Apache 2.0 (huggingface.co) |
| 2 points by helloericsf on May 12, 2024 | past |
|
| 21. | | Snowflake Arctic (snowflake.com) |
| 1 point by helloericsf on April 25, 2024 | past | 1 comment |
|
| 22. | | Training-Free Long-Context Scaling of Large Language Models (arxiv.org) |
| 2 points by helloericsf on April 23, 2024 | past |
|
| 23. | | Multi-agent collaboration design patterns (deeplearning.ai) |
| 2 points by helloericsf on April 18, 2024 | past | 1 comment |
|
| 24. | | Yi-34B, Llama 2, and common practices in LLM training (eleuther.ai) |
| 41 points by helloericsf on April 4, 2024 | past | 3 comments |
|
| 25. | | Cloudflare Calls – Build real-time serverless video, audio and data applications (cloudflare.com) |
| 8 points by helloericsf on April 4, 2024 | past | 1 comment |
|
