microsoft / glinthawkLinks
An LLM inference engine, written in C++
☆18Updated 6 months ago
Alternatives and similar repositories for glinthawk
Users that are interested in glinthawk are comparing it to the libraries listed below
Sorting:
- LLM Serving Performance Evaluation Harness☆82Updated 10 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆136Updated last year
- ☆48Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆50Updated 5 months ago
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆67Updated 2 months ago
- Fast and memory-efficient exact attention☆15Updated this week
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆206Updated last year
- KV cache compression for high-throughput LLM inference☆148Updated 11 months ago
- Efficient Long-context Language Model Training by Core Attention Disaggregation☆75Updated 2 weeks ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 6 months ago
- Accelerate Video Diffusion Inference via Sketching-Rendering Cooperation☆19Updated 7 months ago
- Compression for Foundation Models☆35Updated 5 months ago
- ☆49Updated 8 months ago
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated last month
- 16-fold memory access reduction with nearly no loss☆109Updated 9 months ago
- DeeperGEMM: crazy optimized version☆74Updated 8 months ago
- ☆52Updated 7 months ago
- Microsoft Collective Communication Library☆66Updated last year
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆74Updated last month
- ☆81Updated 2 months ago
- A resilient distributed training framework☆96Updated last year
- Easy, Fast, and Scalable Multimodal AI☆89Updated this week
- AI-Driven Research Systems (ADRS)☆113Updated 3 weeks ago
- PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation☆31Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆175Updated last year
- [Archived] For the latest updates and community contribution, please visit: https://gitcode.com/Ascend/TransferQueue☆12Updated this week
- ☆25Updated last year
- AI model training on heterogeneous, geo-distributed resources☆32Updated last month
- SpotServe: Serving Generative Large Language Models on Preemptible Instances☆134Updated last year
- GPU operators for sparse tensor operations☆35Updated last year