mlc-ai / tokenizers-cppLinks
Universal cross-platform tokenizers binding to HF and sentencepiece
☆342Updated this week
Alternatives and similar repositories for tokenizers-cpp
Users that are interested in tokenizers-cpp are comparing it to the libraries listed below
Sorting:
- ☆66Updated 2 years ago
- ☆194Updated last month
- LLaMa/RWKV onnx models, quantization and testcase☆363Updated last year
- optimized BERT transformer inference on NVIDIA GPU. https://arxiv.org/abs/2210.03052☆473Updated last year
- GPTQ inference Triton kernel☆300Updated 2 years ago
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆172Updated 2 months ago
- ☆139Updated last year
- ☆127Updated 5 months ago
- ☆123Updated last year
- A Toolkit to Help Optimize Onnx Model☆153Updated this week
- Common utilities for ONNX converters☆270Updated 6 months ago
- onnxruntime-extensions: A specialized pre- and post- processing library for ONNX Runtime☆390Updated this week
- llm-export can export llm model to onnx.☆293Updated 4 months ago
- A collection of memory efficient attention operators implemented in the Triton language.☆271Updated last year
- BitBLAS is a library to support mixed-precision matrix multiplications, especially for quantized LLM deployment.☆619Updated last month
- ☆411Updated last year
- The Triton backend for the ONNX Runtime.☆148Updated 3 weeks ago
- Common source, scripts and utilities for creating Triton backends.☆324Updated 3 weeks ago
- The Triton TensorRT-LLM Backend☆845Updated this week
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆831Updated 9 months ago
- Transformer related optimization, including BERT, GPT☆59Updated last year
- A quantization algorithm for LLM☆141Updated 11 months ago
- A Toolkit to Help Optimize Large Onnx Model☆158Updated last year
- Performance of the C++ interface of flash attention and flash attention v2 in large language model (LLM) inference scenarios.☆37Updated 3 months ago
- Fast low-bit matmul kernels in Triton☆311Updated this week
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆124Updated last month
- Easy and Efficient Quantization for Transformers☆198Updated 3 months ago
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆251Updated 7 months ago
- ☆119Updated last year
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆690Updated 3 months ago