brrrrrm
- Karma
- 2,097
- Created
- 4 years ago
About
http://twitter.com/bwastihttp://github.com/bwasti
[all posted thoughts and comments are my own]
Recent Submissions
- 1. ▲ Show HN: Binfer, an experimental LLM inference engine in TypeScript and CUDA (github.com)
- 2. ▲ Five Times Faster (jott.live)
- 3. ▲ Bitwise Consistent On-Policy Reinforcement Learning with VLLM and TorchTitan (blog.vllm.ai)
- 4. ▲ Should we apply old-school multi-core scheduling to GPUs? (jott.live)
- 5. ▲ Show HN: GT: experimental multiplexed distributed tensor framework (github.com)
- 6. ▲ GT – Experimental multiplexing tensor framework for distributed GPU computing (github.com)
- 7. ▲ MFU Is Poorly Approximating Billions of Dollars in Compute (jott.live)
- 8. ▲ Model Flop Utilization Beyond 6ND (jott.live)
- 9. ▲ SWE-bench verified agents may look at future repository state (github.com)
- 10. ▲ Animators Say, 'That's All, Folks' (2000) (nytimes.com)