mlc-ai / llm-perf-benchLinks
☆120Updated last year
Alternatives and similar repositories for llm-perf-bench
Users that are interested in llm-perf-bench are comparing it to the libraries listed below
Sorting:
- A general 2-8 bits quantization toolbox with GPTQ/AWQ/HQQ/VPTQ, and export to onnx/onnx-runtime easily.☆180Updated 6 months ago
- GPTQ inference Triton kernel☆309Updated 2 years ago
- ☆74Updated 6 months ago
- Reorder-based post-training quantization for large language model☆195Updated 2 years ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆320Updated last year
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆265Updated 2 months ago
- ☆199Updated 5 months ago
- An easy-to-use package for implementing SmoothQuant for LLMs☆106Updated 5 months ago
- vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs☆90Updated last week
- ☆121Updated last year
- Easy and Efficient Quantization for Transformers☆203Updated 3 months ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- Advanced Ultra-Low Bitrate Compression Techniques for the LLaMA Family of LLMs☆110Updated last year
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆234Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆82Updated last year
- QQQ is an innovative and hardware-optimized W4A8 quantization solution for LLMs.☆140Updated last month
- The official implementation of the EMNLP 2023 paper LLM-FP4☆215Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated 11 months ago
- scalable and robust tree-based speculative decoding algorithm☆359Updated 8 months ago
- ☆166Updated last week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆383Updated last year
- High-speed GEMV kernels, at most 2.7x speedup compared to pytorch baseline.☆116Updated last year
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆182Updated last year
- A safetensors extension to efficiently store sparse quantized tensors on disk☆164Updated this week
- KV cache compression for high-throughput LLM inference☆141Updated 8 months ago
- ☆95Updated 6 months ago
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆383Updated last year
- PB-LLM: Partially Binarized Large Language Models☆155Updated last year
- LLM Serving Performance Evaluation Harness☆79Updated 7 months ago
- llama INT4 cuda inference with AWQ☆55Updated 8 months ago