shreyansh26 / Speculative-Sampling
Implementation of Speculative Sampling as described in "Accelerating Large Language Model Decoding with Speculative Sampling" by Deepmind
☆86Updated 11 months ago
Alternatives and similar repositories for Speculative-Sampling:
Users that are interested in Speculative-Sampling are comparing it to the libraries listed below
- Explorations into some recent techniques surrounding speculative decoding☆238Updated last month
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆191Updated 2 months ago
- ☆219Updated 9 months ago
- ☆111Updated 4 months ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆157Updated this week
- Spec-Bench: A Comprehensive Benchmark and Unified Evaluation Platform for Speculative Decoding (ACL 2024 Findings)☆222Updated 3 months ago
- ☆40Updated 11 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆107Updated 2 months ago
- LongRoPE is a novel method that can extends the context window of pre-trained LLMs to an impressive 2048k tokens.☆126Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆157Updated 7 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆90Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆84Updated 4 months ago
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆147Updated 3 weeks ago
- Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)☆56Updated 4 months ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆205Updated 5 months ago
- Multi-Candidate Speculative Decoding☆34Updated 9 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆48Updated 7 months ago
- Official PyTorch implementation of DistiLLM: Towards Streamlined Distillation for Large Language Models (ICML 2024)☆183Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆242Updated 2 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆272Updated 3 weeks ago
- Unofficial implementation for the paper "Mixture-of-Depths: Dynamically allocating compute in transformer-based language models"☆145Updated 7 months ago
- Code for Palu: Compressing KV-Cache with Low-Rank Projection☆73Updated 2 weeks ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆293Updated 7 months ago
- Unofficial implementations of block/layer-wise pruning methods for LLMs.☆62Updated 9 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆331Updated 6 months ago
- [ICLR 2025] PEARL: parallel speculative decoding with adaptive draft length☆37Updated 5 months ago
- Triton-based implementation of Sparse Mixture of Experts.☆196Updated 2 months ago
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆306Updated 4 months ago
- The official implementation of the EMNLP 2023 paper LLM-FP4☆180Updated last year
- Low-bit optimizers for PyTorch☆125Updated last year