3 papers
cs.SE2026
The Llama 4 Herd: Architecture, Training, Evaluation, and Deployment Notes
Redacted by arXiv
This document consolidates publicly reported technical details about Metas Llama 4 model family. It summarizes (i) released variants (Scout and Maverick) and the broader herd conte…
cs.CL2025
Efficient Speculative Decoding for Llama at Scale: Challenges and Solutions
Bangsheng Tang, Carl Chengyan Fu, Fei Kou +35
Speculative decoding is a standard method for accelerating the inference speed of large language models. However, scaling it for production environments poses several engineering c…
cs.DC2025
Context Parallelism for Scalable Million-Token Inference
Amy Yang, Jingyi Yang, Aya Ibrahim +6
We present context parallelism for long-context large language model inference, which achieves near-linear scaling for long-context prefill latency with up to 128 H100 GPUs across…