speculative-decoding

7 progetti condividono questo topic GitHub

Le linee collegano membri che sono misurabilmente correlati tra loro. La dimensione dei punti riflette le stelle.

🧬 Membri

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

Large-scale LLM inference engine

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Pure Rust Inference Engine

awesome-on-policy-distillation

A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of…

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

sndr_core_engine

SNDR Core Engine (Genesis) — vLLM runtime patch-overlay for Qwen3.6 + Gemma4 on consumer NVIDIA (Ampere…

🔗 Famiglie affini

llm-inference 76 cuda 90 quantization 51 qwen 102 inference-engine 14 intel 5 lora 65 rocm 13

Misurato dai temi di GitHub condivisi da entrambi i progetti, ponderato in base a quanto è raro ciascun tema.