Hydragen: High-Throughput LLM Inference with Shared Prefixes
☆48May 10, 2024Updated last year
Alternatives and similar repositories for hydragen
Users that are interested in hydragen are comparing it to the libraries listed below
Sorting:
- Symphony — A decentralized multi-agent framework that enables intelligent agents to collaborate seamlessly across heterogeneous edge devi…☆30Oct 30, 2025Updated 4 months ago
- ☆155Mar 4, 2025Updated 11 months ago
- Vocabulary Parallelism☆25Mar 10, 2025Updated 11 months ago
- Code for "Adaptive Self-improvement LLM Agentic System for ML Library Development" (ICML 2025)☆15Jan 6, 2026Updated last month
- Simple RAM benchmark for Linux.☆11Aug 4, 2021Updated 4 years ago
- Codebase for Math Neurosurgery: Isolating LLMs' Math Reasoning Abilities Using Only Forward Passes☆21Jun 15, 2025Updated 8 months ago
- An Attention Superoptimizer☆22Jan 20, 2025Updated last year
- ACM SoCC 2019, "Coupling Decentralized Key-Value Stores with Erasure Coding"☆15May 22, 2021Updated 4 years ago
- ☆15Nov 5, 2024Updated last year
- [ACL 2025 main] FR-Spec: Frequency-Ranked Speculative Sampling☆51Jul 15, 2025Updated 7 months ago
- ☆44Updated this week
- ☆17Sep 15, 2021Updated 4 years ago
- Automating Sub-Agent Creation for Agentic Orchestration☆58Feb 11, 2026Updated 2 weeks ago
- ☆20Dec 24, 2024Updated last year
- Pytorch process group third-party plugin for UCC☆21Apr 15, 2024Updated last year
- ☆224Oct 24, 2025Updated 4 months ago
- extensible collectives library in triton☆95Mar 31, 2025Updated 11 months ago
- Code repo for efficient quantized MoE inference with mixture of low-rank compensators☆31Apr 14, 2025Updated 10 months ago
- ☆44Sep 6, 2021Updated 4 years ago
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆163Feb 11, 2026Updated 2 weeks ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆314Jun 10, 2025Updated 8 months ago
- Query-Adaptive Vector Search☆68Feb 13, 2026Updated 2 weeks ago
- A lightweight, user-friendly data-plane for LLM training.☆38Sep 10, 2025Updated 5 months ago
- A GPU FP32 computation method with Tensor Cores.☆26Dec 8, 2025Updated 2 months ago
- ☆34Jun 22, 2024Updated last year
- [NeurIPS 2024] Fast Best-of-N Decoding via Speculative Rejection☆55Oct 29, 2024Updated last year
- Stateful LLM Serving☆96Mar 11, 2025Updated 11 months ago
- The official implementation of Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresight☆82Jan 16, 2026Updated last month
- ☆118May 19, 2025Updated 9 months ago
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆25May 12, 2025Updated 9 months ago
- ☆21Apr 17, 2025Updated 10 months ago
- PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]☆65Oct 2, 2025Updated 5 months ago
- [HPCA 2026] A GPU-optimized system for efficient long-context LLMs decoding with low-bit KV cache.☆80Dec 18, 2025Updated 2 months ago
- ☆112Sep 25, 2024Updated last year
- An adaptive sampling framework for Reinforce-style LLM post training.☆91Nov 29, 2025Updated 3 months ago
- ☆40Jun 30, 2025Updated 8 months ago
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆446Feb 4, 2026Updated 3 weeks ago
- Triton-based implementation of Sparse Mixture of Experts.☆266Oct 3, 2025Updated 5 months ago
- ☆65Apr 26, 2025Updated 10 months ago