Inference framework for MoE layers based on TensorRT with Python binding
☆40May 31, 2021Updated 5 years ago
Alternatives and similar repositories for InfMoE
Users that are interested in InfMoE are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Compiler for Dynamic Neural Networks☆45Nov 13, 2023Updated 2 years ago
- ☆11Jun 4, 2022Updated 4 years ago
- ☆92Apr 2, 2022Updated 4 years ago
- Official resporitory for "IPDPS' 24 QSync: Quantization-Minimized Synchronous Distributed Training Across Hybrid Devices".☆20Feb 23, 2024Updated 2 years ago
- PilotFish harvests the free GPU cycles of cloud gaming with deep learning training☆14Jul 2, 2022Updated 4 years ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- PET: Optimizing Tensor Programs with Partially Equivalent Transformations and Automated Corrections☆126Jun 23, 2022Updated 4 years ago
- Adaptive Message Quantization and Parallelization for Distributed Full-graph GNN Training☆24Mar 1, 2024Updated 2 years ago
- A fast MoE impl for PyTorch☆1,859Feb 10, 2025Updated last year
- A language and compiler for irregular tensor programs.☆153Sep 18, 2026Updated last month
- ☆17Apr 16, 2026Updated 6 months ago
- A hybrid partitioner based quantum circuit simulation system on GPU☆46Aug 17, 2022Updated 4 years ago
- A plug-in of Microsoft DeepSpeed to fix the bug of DeepSpeed pipeline☆25Apr 16, 2021Updated 5 years ago
- ☆12Apr 3, 2023Updated 3 years ago
- A hand-written recursive decent Verilog parser.☆10Jun 28, 2026Updated 4 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.
- Write pandoc markdown in OverLeaf☆12Sep 28, 2022Updated 4 years ago
- Explore Inter-layer Expert Affinity in MoE Model Inference☆17May 6, 2024Updated 2 years ago
- Compiling finite generators to digital logic. WIP☆13Aug 24, 2020Updated 6 years ago
- Surrogate-based Hyperparameter Tuning System☆30Jun 29, 2023Updated 3 years ago
- ☆11Updated this week
- A simple MIPS CPU for BUAA CO course (and now NSCSCC).☆10May 15, 2021Updated 5 years ago
- A router IP written in Verilog.☆12Dec 20, 2019Updated 6 years ago
- ☆51Dec 26, 2024Updated last year
- ☆84Feb 5, 2026Updated 8 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.
- Mini-SGLang is a mini version of SGLang project ().☆13Sep 24, 2025Updated last year
- ☆14Jun 16, 2026Updated 4 months ago
- Resource Multiplexing in Tuning and Serving Large Language Models (USENIX ATC 2025)☆10Apr 21, 2026Updated 6 months ago
- An agent for CUDA compute-communication kernel co-design☆37May 7, 2026Updated 5 months ago
- Benchmark PyTorch Custom Operators☆14Jul 6, 2023Updated 3 years ago
- Documentation for TCP Lab☆12Oct 23, 2026Updated last week
- Let's discover a new world. — Edit☆10Jan 6, 2017Updated 9 years ago
- Official Repo for "SplitQuant / LLM-PQ: Resource-Efficient LLM Offline Serving on Heterogeneous GPUs via Phase-Aware Model Partition and …☆41Aug 29, 2025Updated last year
- A lightweight CuTe-based CUDA kernel for DuoAttention, optimized for large language model inference.☆12Dec 25, 2025Updated 10 months ago
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- An auxiliary project analysis of the characteristics of KV in DiT Attention.☆34Nov 29, 2024Updated last year
- Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]☆25Nov 21, 2024Updated last year
- 3M: Multi-loss, Multi-path and Multi-level Neural Networks for speech recognition☆120Jun 22, 2022Updated 4 years ago
- ☆20Jan 9, 2025Updated last year
- A Cluster-Wide Model Manager to Accelerate DNN Training via Automated Training Warmup☆36Jan 9, 2023Updated 3 years ago
- This is the implementation repository of our SOSP'24 paper: Aceso: Achieving Efficient Fault Tolerance in Memory-Disaggregated Key-Value …☆24Oct 20, 2024Updated 2 years ago
- ☆29Aug 14, 2024Updated 2 years ago