logotype
- Karma
- 377
- Created
- 14 years ago
About
intentionally left blank.Recent Submissions
- 1. ▲ Speculative pre-positioning: off-path decode for stateful inference sessions (arxiv.org)
- 2. ▲ Stateful Inference for Low-Latency Multi-Agent Tool Calling (arxiv.org)
- 3. ▲ Attention Once Is All You Need: Stateful Transformers (arxiv.org)
- 4. ▲ New inference engine faster than vLLM, SGLang, TRT-LLM (layerscale.ai)