A PyTorch native library for training speculative decoding models
Like lightseekorg/TorchSpec, 0 likes 0 Bookmark lightseekorg/TorchSpec, 0 bookmarks 0 DeepSpec: a full-stack codebase for training and evaluating speculative decoding algorithms
Like deepseek-ai/DeepSpec, 0 likes 0 Bookmark deepseek-ai/DeepSpec, 0 bookmarks 0 A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Like vllm-project/speculators, 0 likes 0 Bookmark vllm-project/speculators, 0 bookmarks 0 Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Like sgl-project/SpecForge, 0 likes 0 Bookmark sgl-project/SpecForge, 0 bookmarks 0 SpecOPD: Branch-parallel on-policy distillation for faster speculative decoding.
Like QwenApp/SpecOPD, 0 likes 0 Bookmark QwenApp/SpecOPD, 0 bookmarks 0 A unified, torch-native training framework for MTP and block-parallel speculative decoding.
Like Tencent/AngelSpec, 0 likes 0 Bookmark Tencent/AngelSpec, 0 bookmarks 0 Speculative decoding has plenty of tricks. Which ones actually make LLMs faster? Explore 7 methods, 26 checkpoints, and a shared training and evaluation framework.
Like ernie-research/DCore, 0 likes 0 Bookmark ernie-research/DCore, 0 bookmarks 0 SpecPilot: Autonomous Algorithm Discovery and Systems Optimization for Speculative Decoding
Like StargazerX0/SpecPilot, 0 likes 0 Bookmark StargazerX0/SpecPilot, 0 bookmarks 0 The official repo of "Draft-OPD: On-Policy Distillation for Speculative Draft Models"
Like Simplified-Reasoning/Draft-OPD, 0 likes 0 Bookmark Simplified-Reasoning/Draft-OPD, 0 bookmarks 0