vllm-project / speculatorsLinks
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
☆65Updated this week
Alternatives and similar repositories for speculators
Users that are interested in speculators are comparing it to the libraries listed below
Sorting:
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆299Updated this week
- KV cache compression for high-throughput LLM inference☆143Updated 9 months ago
- vLLM performance dashboard☆37Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated last year
- Benchmark suite for LLMs from Fireworks.ai☆83Updated 2 weeks ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆241Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆130Updated 11 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆204Updated this week
- Code for data-aware compression of DeepSeek models☆63Updated last week
- ☆56Updated 11 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆85Updated last year
- [NeurIPS 2025] Simple extension on vLLM to help you speed up reasoning model without training.☆203Updated 5 months ago
- LLM Serving Performance Evaluation Harness☆80Updated 8 months ago
- ☆205Updated 6 months ago
- Efficient LLM Inference over Long Sequences☆390Updated 4 months ago
- QuIP quantization☆59Updated last year
- ☆106Updated last week
- Easy and Efficient Quantization for Transformers☆202Updated 4 months ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆180Updated 7 months ago
- 3x Faster Inference; Unofficial implementation of EAGLE Speculative Decoding☆78Updated 4 months ago
- A pipeline for LLM knowledge distillation☆109Updated 7 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆169Updated last year
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆111Updated 7 months ago
- Accelerating your LLM training to full speed! Made with ❤️ by ServiceNow Research☆258Updated last week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆390Updated last year
- vLLM adapter for a TGIS-compatible gRPC server.☆44Updated this week
- Inference server benchmarking tool☆128Updated last month
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆346Updated 6 months ago
- Official implementation for Training LLMs with MXFP4☆101Updated 6 months ago
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆147Updated last year