Hydragen: High-Throughput LLM Inference with Shared Prefixes
☆56May 10, 2024Updated 2 years ago
Alternatives and similar repositories for hydragen
Users that are interested in hydragen are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆16Jun 15, 2026Updated last month
- Simple, flexible configuration in pure Python!☆32Jul 1, 2025Updated last year
- ☆156Mar 4, 2025Updated last year
- Archon provides a modular framework for combining different inference-time techniques and LMs with just a JSON config file.☆207Mar 7, 2025Updated last year
- ☆32Mar 24, 2025Updated last year
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- ☆117Sep 25, 2024Updated last year
- ☆60Feb 24, 2026Updated 5 months ago
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆57Aug 6, 2025Updated 11 months ago
- [ICML 2025] Adaptive Self-improvement LLM Agentic System for ML Library Development☆17Jan 6, 2026Updated 6 months ago
- ☆59Jan 28, 2025Updated last year
- ☆16Aug 7, 2023Updated 2 years ago
- A Triton-only attention backend for vLLM☆27Jul 14, 2026Updated last week
- Vocabulary Parallelism☆26Mar 10, 2025Updated last year
- Tile-based language built for AI computation across all scales☆176Jun 16, 2026Updated last month
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Codebase for ICML submission "DOGE: Domain Reweighting with Generalization Estimation"☆21Feb 29, 2024Updated 2 years ago
- SGLang kernel library for Intel XPU☆27Updated this week
- Simple RAM benchmark for Linux.☆12Aug 4, 2021Updated 4 years ago
- vLLM adapter for a TGIS-compatible gRPC server.☆55Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆329Jun 10, 2025Updated last year
- ☆18Sep 23, 2025Updated 10 months ago
- ☆483Nov 25, 2025Updated 8 months ago
- TurboServe: Serving Streaming Video Generation Efficiently and Economically☆37Jul 12, 2026Updated last week
- Query-Adaptive Vector Search☆77Mar 19, 2026Updated 4 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆80Nov 26, 2024Updated last year
- ☆44Jul 1, 2026Updated 3 weeks ago
- ☆22Apr 17, 2025Updated last year
- NVSHMEM‑Tutorial: Build a DeepEP‑like GPU Buffer☆195Feb 11, 2026Updated 5 months ago
- Github mirror of trition-lang/triton repo.☆181Updated this week
- Stateful LLM Serving☆105Mar 11, 2025Updated last year
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆344Jul 2, 2024Updated 2 years ago
- ☆41May 26, 2026Updated last month
- Repo hosting codes and materials related to speeding LLMs' inference using token merging.☆37Oct 9, 2025Updated 9 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- extensible collectives library in triton☆97Mar 31, 2025Updated last year
- Al Quran is the holy book of Islam. Muslims believe that the Quran was revealed by Allah (SWT) to the final prophet & messenger, Muhammad…☆12Apr 30, 2023Updated 3 years ago
- code for EMNLP 2024 paper: Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis☆12Nov 17, 2024Updated last year
- Prefix-Aware Attention for LLM Decoding☆41May 26, 2026Updated last month
- FPGA Labs for EECS 151/251A (Fall 2021)☆13Oct 20, 2021Updated 4 years ago
- Implementation of an efficient LLM architecture: the Pair-In / Pair-Out Model (PIPO)☆42Jun 10, 2026Updated last month
- ☆18Nov 28, 2024Updated last year