lucidrains / speculative-decoding
Explorations into some recent techniques surrounding speculative decoding
☆259Updated 4 months ago
Alternatives and similar repositories for speculative-decoding:
Users that are interested in speculative-decoding are comparing it to the libraries listed below
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆258Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆340Updated 8 months ago
- ☆237Updated 11 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆199Updated 4 months ago
- ☆219Updated 10 months ago
- Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind☆93Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆304Updated 9 months ago
- ☆313Updated last year
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆183Updated 2 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆288Updated 3 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆93Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆209Updated 8 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆270Updated 5 months ago
- ☆122Updated 2 months ago
- [NeurIPS'23] H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models.☆438Updated 8 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆210Updated 4 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆207Updated last month
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆90Updated last year
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆158Updated 10 months ago
- Code repo for the paper "LLM-QAT Data-Free Quantization Aware Training for Large Language Models"☆280Updated last month
- Official Implementation of "Learning Harmonized Representations for Speculative Sampling" (HASS)☆31Updated last month
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆102Updated last month
- Official PyTorch implementation of QA-LoRA☆131Updated last year
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆240Updated last week
- ☆197Updated 4 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago
- 📰 Must-read papers on KV Cache Compression (constantly updating 🤗).☆376Updated 2 weeks ago
- ☆43Updated last year
- 📰 Must-read papers and blogs on Speculative Decoding ⚡️☆696Updated last week