vllm-project / speculatorsLinks
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
☆220Updated 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☆384Updated this week
- Genai-bench is a powerful benchmark tool designed for comprehensive token-level performance evaluation of large language model (LLM) serv…☆260Updated last week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆267Updated 2 months ago
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆272Updated last week
- Efficient LLM Inference over Long Sequences☆394Updated 7 months ago
- ☆206Updated 8 months ago
- KV cache compression for high-throughput LLM inference☆151Updated last year
- vLLM performance dashboard☆40Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆238Updated this week
- Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support☆266Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆93Updated last year
- Easy and Efficient Quantization for Transformers☆204Updated last week
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆137Updated last year
- Code for data-aware compression of DeepSeek models☆69Updated last month
- TPU inference for vLLM, with unified JAX and PyTorch support.☆223Updated last week
- Benchmark suite for LLMs from Fireworks.ai☆89Updated this week
- LLM Serving Performance Evaluation Harness☆83Updated 11 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆219Updated last week
- ☆125Updated last year
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆279Updated 2 months ago
- Applied AI experiments and examples for PyTorch☆315Updated 5 months ago
- ☆96Updated 10 months ago
- An early research stage expert-parallel load balancer for MoE models based on linear programming.☆495Updated 2 months ago
- Fast low-bit matmul kernels in Triton☆424Updated last week
- ☆219Updated last year
- QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference☆120Updated last year
- LM engine is a library for pretraining/finetuning LLMs☆113Updated this week
- A high-performance and light-weight router for vLLM large scale deployment☆101Updated this week
- Load compute kernels from the Hub☆389Updated this week
- a minimal cache manager for PagedAttention, on top of llama3.☆135Updated last year