ScalingIntelligence / hydragenLinks
Hydragen: High-Throughput LLM Inference with Shared Prefixes
☆45Updated last year
Alternatives and similar repositories for hydragen
Users that are interested in hydragen are comparing it to the libraries listed below
Sorting:
- Autonomous GPU Kernel Generation via Deep Agents☆179Updated this week
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆170Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆86Updated last year
- Framework to reduce autotune overhead to zero for well known deployments.☆90Updated 2 months ago
- ☆114Updated 6 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- ☆155Updated 10 months ago
- TritonBench: Benchmarking Large Language Model Capabilities for Generating Triton Operators☆98Updated 6 months ago
- PyTorch bindings for CUTLASS grouped GEMM.☆132Updated 6 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- Ship correct and fast LLM kernels to PyTorch☆126Updated this week
- ☆52Updated 6 months ago
- ☆97Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆246Updated last year
- ☆96Updated last year
- ☆113Updated last year
- Building the Virtuous Cycle for AI-driven LLM Systems☆95Updated last week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆156Updated 2 months ago
- ☆65Updated 7 months ago
- QuTLASS: CUTLASS-Powered Quantized BLAS for Deep Learning☆145Updated last month
- ☆132Updated 6 months ago
- DeeperGEMM: crazy optimized version☆73Updated 7 months ago
- Flash-LLM: Enabling Cost-Effective and Highly-Efficient Large Generative Model Inference with Unstructured Sparsity☆230Updated 2 years ago
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year
- Triton-based Symmetric Memory operators and examples☆65Updated last month
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆56Updated last month
- extensible collectives library in triton☆91Updated 8 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆331Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago