FP8 LLMs for vLLM Collection Accurate FP8 quantized models by Neural Magic, ready for use with vLLM! • 44 items • Updated Oct 17, 2024 • 65
Skywork: A More Open Bilingual Foundation Model Paper • 2310.19341 • Published Oct 30, 2023 • 6
Skywork-MoE: A Deep Dive into Training Techniques for Mixture-of-Experts Language Models Paper • 2406.06563 • Published Jun 3, 2024 • 19