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 9 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆135Updated last year
- ☆48Updated last year
- Efficient Compute-Communication Overlap for Distributed LLM Inference☆66Updated last month
- [OSDI'24] Serving LLM-based Applications Efficiently with Semantic Variable☆203Updated last year
- [ICLR 2025] TidalDecode: A Fast and Accurate LLM Decoding with Position Persistent Sparse Attention☆49Updated 4 months ago
- ☆79Updated 2 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆51Updated 5 months ago
- Fast and memory-efficient exact attention☆14Updated this week
- Stateful LLM Serving☆90Updated 9 months ago
- 16-fold memory access reduction with nearly no loss☆109Updated 8 months ago
- ☆83Updated 8 months ago
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆249Updated last year
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆172Updated last year
- [NeurIPS 2024] Efficient LLM Scheduling by Learning to Rank☆66Updated last year
- ☆52Updated 7 months ago
- 🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation…☆107Updated last month
- Vortex: A Flexible and Efficient Sparse Attention Framework☆43Updated 2 weeks ago
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆62Updated 2 weeks ago
- Dynamic Context Selection for Efficient Long-Context LLMs☆47Updated 7 months ago
- KV cache compression for high-throughput LLM inference☆148Updated 10 months ago
- ☆34Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆86Updated last year
- A Suite for Parallel Inference of Diffusion Transformers (DiTs) on multi-GPU Clusters☆52Updated last year
- Easy, Fast, and Scalable Multimodal AI☆79Updated this week
- [NeurIPS 2025] Scaling Speculative Decoding with Lookahead Reasoning☆56Updated last month
- Beyond KV Caching: Shared Attention for Efficient LLMs☆20Updated last year
- Scalable long-context LLM decoding that leverages sparsity—by treating the KV cache as a vector storage system.☆106Updated 3 months ago
- ☆70Updated 3 months ago
- A resilient distributed training framework☆96Updated last year