mji

Recent Submissions

1. 1. ▲ DeepSeek-V4 on Day 0: From Fast Inference to Verified RL with SGLang and Miles (lmsys.org) 80 points · 1 month ago · 10 comments
2. 2. ▲ TorchTPU: Running PyTorch Natively on TPUs at Google Scale (developers.googleblog.com) 206 points · 1 month ago · 18 comments
3. 3. ▲ RvLLM: High-performance LLM inference in Rust (github.com) 3 points · 2 months ago · 0 comments
4. 4. ▲ My chief of staff, Claude Code (twitter.com) 3 points · 3 months ago · 6 comments
5. 5. ▲ Native KV Cache Offloading to Any Filesystem with LLM-D (llm-d.ai) 2 points · 3 months ago · 0 comments
6. 6. ▲ Mooncake Joins PyTorch Ecosystem (pytorch.org) 1 point · 3 months ago · 0 comments
7. 7. ▲ The K-Shaped Future of Software Engineering (twitter.com) 1 point · 4 months ago · 0 comments
8. 8. ▲ How Prompt Caching Works – Paged Attention and Automatic Prefix Caching (sankalp.bearblog.dev) 6 points · 6 months ago · 0 comments
9. 9. ▲ California lawmakers pass SB 79, housing bill that brings dense housing (latimes.com) 238 points · 9 months ago · 127 comments
10. 10. ▲ Reinforcement Learning with Nvidia NeMo-RL (nvidia-nemo.github.io) 3 points · 11 months ago · 0 comments