raymin0223 / fast_robust_early_exitView external linksLinks
Fast and Robust Early-Exiting Framework for Autoregressive Language Models with Synchronized Parallel Decoding (EMNLP 2023 Long)
☆65Sep 28, 2024Updated last year
Alternatives and similar repositories for fast_robust_early_exit
Users that are interested in fast_robust_early_exit are comparing it to the libraries listed below
Sorting:
- Official repository of "Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions", ICLR 2024 Sp…☆21Mar 7, 2024Updated last year
- EE-LLM is a framework for large-scale training and inference of early-exit (EE) large language models (LLMs).☆74Jun 14, 2024Updated last year
- Multi-Candidate Speculative Decoding☆39Apr 22, 2024Updated last year
- [EMNLP 2023]Context Compression for Auto-regressive Transformers with Sentinel Tokens☆25Nov 6, 2023Updated 2 years ago
- Code associated with the paper **Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding**☆214Feb 13, 2025Updated last year
- ☆12Feb 5, 2026Updated last week
- Official code for the paper "Attention as a Hypernetwork"☆47Jun 22, 2024Updated last year
- ☆158Feb 15, 2025Updated last year
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Jul 19, 2024Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆357Feb 5, 2026Updated last week
- [NeurIPS'23] Speculative Decoding with Big Little Decoder☆96Feb 6, 2024Updated 2 years ago
- Efficient retrieval head analysis with triton flash attention that supports topK probability☆13Jun 15, 2024Updated last year
- ☆16Dec 21, 2023Updated 2 years ago
- See https://github.com/cuda-mode/triton-index/ instead!☆11May 8, 2024Updated last year
- ☆26Nov 23, 2023Updated 2 years ago
- ☆352Apr 2, 2024Updated last year
- QAQ: Quality Adaptive Quantization for LLM KV Cache☆55Mar 27, 2024Updated last year
- ☆13Dec 15, 2025Updated 2 months ago
- Code and dataset for EMNLP 2022 Findings paper "Benchmarking Language Models for Code Syntax Understanding"☆16Oct 24, 2022Updated 3 years ago
- Simple (fast) transformer inference in PyTorch with torch.compile + lit-llama code☆10Aug 29, 2023Updated 2 years ago
- ☆53May 13, 2024Updated last year
- An innovative method expediting LLMs via streamlined semi-autoregressive generation and draft verification.☆26Apr 15, 2025Updated 10 months ago
- My Implementation of Q-Sparse: All Large Language Models can be Fully Sparsely-Activated☆33Aug 14, 2024Updated last year
- Implementation of IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs (ICLR 2024).☆25Jul 15, 2025Updated 7 months ago
- ☆129Jan 22, 2024Updated 2 years ago
- ☆83Dec 1, 2023Updated 2 years ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆214Sep 11, 2025Updated 5 months ago
- ☆16Dec 9, 2023Updated 2 years ago
- Building language models to predict more than one token ahead to enable further ahead predictions.☆12May 22, 2025Updated 8 months ago
- [EMNLP 2023] Official implementation of the algorithm ETSC: Exact Toeplitz-to-SSM Conversion our EMNLP 2023 paper - Accelerating Toeplitz…☆14Oct 17, 2023Updated 2 years ago
- Source code for a LoRA-based continual relation extraction method.☆14Sep 25, 2023Updated 2 years ago
- [NeurIPS 2025 Spotlight] Implementation of "KLASS: KL-Guided Fast Inference in Masked Diffusion Models"☆22Jan 3, 2026Updated last month
- Repository for the COLM 2025 paper SpecDec++: Boosting Speculative Decoding via Adaptive Candidate Lengths☆15Jul 10, 2025Updated 7 months ago
- [COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding☆276Aug 31, 2024Updated last year
- [EMNLP'24] LongHeads: Multi-Head Attention is Secretly a Long Context Processor☆31Apr 8, 2024Updated last year
- Cascade Speculative Drafting☆32Apr 2, 2024Updated last year
- [ICLR 2023] "Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers" by Tianlong Chen*, Zhenyu Zhang*, Ajay Jaiswal…☆56Feb 28, 2023Updated 2 years ago
- Hi-Speed DNN Training with Espresso: Unleashing the Full Potential of Gradient Compression with Near-Optimal Usage Strategies (EuroSys '2…☆15Sep 21, 2023Updated 2 years ago
- Benchmark tests supporting the TiledCUDA library.☆18Nov 19, 2024Updated last year