MDK8888 / vllminiLinks
A minimal implementation of vllm.
☆43Updated 10 months ago
Alternatives and similar repositories for vllmini
Users that are interested in vllmini are comparing it to the libraries listed below
Sorting:
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- a minimal cache manager for PagedAttention, on top of llama3.☆91Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆99Updated 2 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆163Updated 11 months ago
- ☆86Updated 2 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆214Updated last year
- ☆54Updated last year
- PyTorch bindings for CUTLASS grouped GEMM.☆99Updated 3 weeks ago
- [ICLR 2025] PEARL: Parallel Speculative Decoding with Adaptive Draft Length☆89Updated 2 months ago
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆48Updated 7 months ago
- A resilient distributed training framework☆95Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆79Updated 9 months ago
- Official repository for DistFlashAttn: Distributed Memory-efficient Attention for Long-context LLMs Training☆210Updated 10 months ago
- ☆62Updated last year
- ☆256Updated last year
- DeeperGEMM: crazy optimized version☆69Updated last month
- ☆60Updated last month
- ☆105Updated 9 months ago
- ☆77Updated 2 months ago
- [NeurIPS 2024] The official implementation of "Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exitin…☆57Updated 11 months ago
- Tritonbench is a collection of PyTorch custom operators with example inputs to measure their performance.☆136Updated this week
- ☆84Updated 3 years ago
- A lightweight design for computation-communication overlap.☆143Updated this week
- PyTorch implementation of paper "Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline".☆88Updated 2 years ago
- ☆114Updated 3 weeks ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- ☆81Updated 7 months ago
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆52Updated last week
- ☆75Updated 5 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆310Updated 11 months ago