IsaacRe / vllm-kvcompress
KV cache compression for high-throughput LLM inference
☆119Updated last month
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☆111Updated 4 months ago
- ☆122Updated last month
- [ICML 2024] KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache☆284Updated 2 months ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆338Updated 7 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆72Updated 6 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆301Updated 9 months ago
- ☆234Updated 11 months ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆236Updated last month
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆158Updated 8 months ago
- 16-fold memory access reduction with nearly no loss☆86Updated last week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆66Updated last week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆202Updated 4 months ago
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆110Updated 3 weeks ago
- Ouroboros: Speculative Decoding with Large Model Enhanced Drafting (EMNLP 2024 main)☆90Updated 2 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆265Updated 4 months ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆94Updated last month
- Layer-Condensed KV cache w/ 10 times larger batch size, fewer params and less computation. Dramatic speed up with better task performance…☆148Updated 2 months ago
- Fast low-bit matmul kernels in Triton☆275Updated this week
- ☆205Updated 2 months ago
- ☆113Updated last week
- PyTorch bindings for CUTLASS grouped GEMM.☆77Updated 5 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆95Updated 10 months ago
- Simple extension on vLLM to help you speed up reasoning model without training.☆139Updated 3 weeks ago
- Official repository for LightSeq: Sequence Level Parallelism for Distributed Training of Long Context Transformers☆207Updated 7 months ago
- REST: Retrieval-Based Speculative Decoding, NAACL 2024☆198Updated 4 months ago
- ☆76Updated last week
- The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆123Updated 3 months ago
- LLM Serving Performance Evaluation Harness☆73Updated last month
- Odysseus: Playground of LLM Sequence Parallelism☆68Updated 9 months ago
- Simple implementation of Speculative Sampling in NumPy for GPT-2.☆92Updated last year