mlc-ai / xgrammar
Efficient, Flexible and Portable Structured Generation
☆125Updated this week
Related projects ⓘ
Alternatives and complementary repositories for xgrammar
- Materials for learning SGLang☆110Updated this week
- Applied AI experiments and examples for PyTorch☆168Updated 3 weeks ago
- ☆101Updated last month
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- ☆115Updated 7 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated last week
- Simple and fast low-bit matmul kernels in CUDA / Triton☆147Updated this week
- KV cache compression for high-throughput LLM inference☆87Updated last week
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆278Updated 4 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- A high-throughput and memory-efficient inference and serving engine for LLMs☆253Updated last month
- A safetensors extension to efficiently store sparse quantized tensors on disk☆51Updated this week
- Fast Inference of MoE Models with CPU-GPU Orchestration☆173Updated this week
- ☆158Updated last month
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆305Updated 3 months ago
- LLM Serving Performance Evaluation Harness☆57Updated 2 months ago
- ☆36Updated 2 weeks ago
- ring-attention experiments☆97Updated last month
- extensible collectives library in triton☆72Updated 2 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆211Updated 3 weeks ago
- Cataloging released Triton kernels.☆138Updated 2 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆166Updated this week
- Making Long-Context LLM Inference 10x Faster and 10x Cheaper☆240Updated this week
- Experiments on speculative sampling with Llama models☆118Updated last year
- Dynamic Memory Management for Serving LLMs without PagedAttention☆240Updated last week
- Modular and structured prompt caching for low-latency LLM inference☆69Updated 2 weeks ago
- ☆45Updated 2 weeks ago
- A low-latency & high-throughput serving engine for LLMs☆247Updated 2 months ago
- ☆189Updated 6 months ago
- ☆88Updated 2 months ago