HN Explorer

helloericsf

↗ HN profile [ 68.9 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Context Engineering for AI Agents: Lessons (manus.im)
    120 points 3
  2. Context Engineering for AI Agents: Lessons (manus.im)
    3 points 0
  3. Better than DeepSeek R1? MiniMax-M1:open-weight hybrid-attention reasoning model (huggingface.co)
    6 points 0
  4. kit - Code Intelligence Toolkit (github.com)
    1 points 0
  5. DeepSeek Open Source Optimized Parallelism Strategies, 3 repos (github.com)
    103 points 9
  6. DeepSeek Open Source DeepGEMM – FP8 GEMM Library(300 lines for 1350+ FP8 TFLOPS) (twitter.com)
    4 points 1
  7. Alibaba Open Source Large-Scale Video Generative Models: Wan2.1 (twitter.com)
    8 points 4
  8. DeepSeek open source DeepEP – library for MoE training and Inference (github.com)
    536 points 76
  9. DeepSeek Open Source FlashMLA – MLA Decoding Kernel for Hopper GPUs (github.com)
    441 points 116
  10. New Qwen2.5-Max Outperforms DeepSeek V3 in Benchmarks (twitter.com)
    3 points 2
  11. Longest context up to 4M, MiniMax-01 hybrid 456B Open source model (github.com)
    19 points 1
  12. DeepSeek v3 beats Claude sonnet 3.5 and way cheaper (huggingface.co)
    48 points 9
  13. NeurIPS and Dr. Picard released statement for singling out Chinese scholars (twitter.com)
    2 points 2
  14. Tencent Hunyuan-Large (github.com)
    148 points 115
  15. Chinese AI Community: open-source Heatmap (huggingface.co)
    1 points 3
  16. Poolside is raising $400M+ at a $2B valuation to build a coding co-pilot (techcrunch.com)
    3 points 1
  17. Is LMDeploy the Ultimate Solution? Why It Outshines VLLM, TRT-LLM, TGI, and MLC (bentoml.com)
    16 points 9
  18. 25 points 2
  19. 21.2× faster than llama.cpp? plus 40% memory usage reduction (arxiv.org)
    43 points 16
  20. Databricks acquires Tabular, Snowflake fork Iceberg? (datagravity.dev)
    2 points 3
  21. New Yi 1.5 models under Apache 2.0 (huggingface.co)
    2 points 1
  22. Snowflake Arctic (snowflake.com)
    1 points 1
  23. Training-Free Long-Context Scaling of Large Language Models (arxiv.org)
    2 points 0
  24. Multi-agent collaboration design patterns (deeplearning.ai)
    2 points 1
  25. Yi-34B, Llama 2, and common practices in LLM training (blog.eleuther.ai)
    41 points 4