Prefix-Aware Attention for LLM Decoding
☆45May 26, 2026Updated 3 months ago
Alternatives and similar repositories for PAT
Users that are interested in PAT are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- An Open-Source RAG Workload Trace to Optimize RAG Serving Systems☆37Nov 18, 2025Updated 9 months ago
- ☆37Updated this week
- ☆36Jul 27, 2026Updated last month
- Artifact Evaluation for SOSP 2025☆22Aug 16, 2025Updated last year
- ☆168Apr 23, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆119Dec 2, 2025Updated 8 months ago
- ☆55Dec 19, 2025Updated 8 months ago
- Boosting GPU utilization for LLM serving via dynamic spatial-temporal prefill & decode orchestration☆52Jan 8, 2026Updated 7 months ago
- ☆39Updated this week
- ☆19Feb 9, 2026Updated 6 months ago
- [IEEE CAL 2025] Accelerating Page Migrations in Operating Systems with Intel DSA☆16Nov 20, 2024Updated last year
- ☆22Jul 13, 2026Updated last month
- An End-to-End Benchmarking Framework for Retrieval-Augmented Generation Systems☆29Mar 13, 2026Updated 5 months ago
- Repo to replay Qwen trace☆33Jan 9, 2026Updated 7 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Supplemental materials for The ASPLOS 2025 / EuroSys 2025 Contest on Intra-Operator Parallelism for Distributed Deep Learning☆25May 12, 2025Updated last year
- ☆25Jan 18, 2026Updated 7 months ago
- This repo is used to assess NSL's scientific research assistants.☆19Jul 7, 2025Updated last year
- Autonomous CUDA kernel optimization agent with structured task specs and per-config scoring☆17Jun 17, 2026Updated 2 months ago
- ☆14Apr 24, 2024Updated 2 years ago
- A lightweight and fast LLM serving framework☆15Mar 5, 2026Updated 5 months ago
- Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation☆42Aug 17, 2026Updated last week
- ☆32Mar 24, 2025Updated last year
- Artifact of Chimera☆18May 6, 2025Updated last year
- 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.
- [PACT'24] GraNNDis. A fast and unified distributed graph neural network (GNN) training framework for both full-batch (full-graph) and min…☆10Aug 13, 2024Updated 2 years ago
- Daily Arxiv Papers on LLM Systems☆80Updated this week
- ☆26Apr 13, 2025Updated last year
- ☆25May 2, 2026Updated 3 months ago
- Agent application/benchmark/workload traces should be placed here.☆15Apr 13, 2026Updated 4 months ago
- DeDe (OSDI '25): an optimization framework for large-scale resource allocation☆15May 18, 2026Updated 3 months ago
- PPoPP24 AGAThA: Fast and Efficient GPU Acceleration of Guided Sequence Alignment for Long Read Mapping☆22May 8, 2024Updated 2 years ago
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆24Nov 21, 2024Updated last year
- ☆34Sep 9, 2020Updated 5 years ago
- 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.
- Research prototype of PRISM — a cost-efficient multi-LLM serving system with flexible time- and space-based GPU sharing.☆77Mar 17, 2026Updated 5 months ago
- On demand communication☆33Apr 16, 2026Updated 4 months ago
- Dynamic Memory Management for Serving LLMs without PagedAttention☆517Updated this week
- ☆44Sep 3, 2025Updated 11 months ago
- SiMM: Scalable in-Memory Middleware☆42Apr 20, 2026Updated 4 months ago
- ☆13Oct 6, 2024Updated last year
- ☆122Updated this week