NickL77 / BaldEagleLinks
3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding
☆58Updated last week
Alternatives and similar repositories for BaldEagle
Users that are interested in BaldEagle are comparing it to the libraries listed below
Sorting:
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆106Updated 2 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- KV cache compression for high-throughput LLM inference☆129Updated 4 months ago
- ☆252Updated last year
- Codes for the paper "∞Bench: Extending Long Context Evaluation Beyond 100K Tokens": https://arxiv.org/abs/2402.13718☆326Updated 8 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆202Updated 6 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆76Updated 9 months ago
- ☆194Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 10 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 9 months ago
- Positional Skip-wise Training for Efficient Context Window Extension of LLMs to Extremely Length (ICLR 2024)☆203Updated last year
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization