IsaacRe / vllm-kvcompress
KV cache compression for high-throughput LLM inference
☆126Updated 2 months ago
Alternatives and similar repositories for vllm-kvcompress:
Users that are interested in vllm-kvcompress are comparing it to the libraries listed below
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆115Updated 4 months ago
- ☆122Updated 2 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆305Updated 9 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆340Updated 8 months ago
- ☆237Updated 11 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 7 months ago
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆288Updated 3 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆159Updated 9 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆94Updated last week
- ☆82Updated last month
- ☆126Updated last month
- A low-latency & high-throughput serving engine for LLMs☆346Updated last week
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆102Updated last month
- Perplexity GPU Kernels☆251Updated this week
- Efficient triton implementation of Native Sparse Attention.☆139Updated 2 weeks ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆248Updated 5 months ago
- Fast low-bit matmul kernels in Triton☆291Updated this week
- 16-fold memory access reduction with nearly no loss☆90Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆81Updated 5 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆206Updated last year
- An easy-to-use package for implementing SmoothQuant for LLMs☆96Updated 2 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆273Updated 5 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆99Updated 2 months ago
- ☆186Updated 6 months ago
- LLM Serving Performance Evaluation Harness☆77Updated 2 months ago
- PyTorch library for cost-effective, fast and easy serving of MoE models.☆171Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆208Updated 5 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆354Updated last week
- ☆56Updated last week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆116Updated 2 weeks ago