apple / ml-recurrent-drafter
☆195Updated 3 weeks ago
Alternatives and similar repositories for ml-recurrent-drafter:
Users that are interested in ml-recurrent-drafter are comparing it to the libraries listed below
- Fast low-bit matmul kernels in Triton☆231Updated this week
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆228Updated this week
- A high-throughput and memory-efficient inference and serving engine for LLMs☆259Updated 4 months ago
- Applied AI experiments and examples for PyTorch☆223Updated this week
- KV cache compression for high-throughput LLM inference☆114Updated last week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆221Updated this week
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆265Updated last year
- LLM KV cache compression made easy☆384Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆64Updated 5 months ago
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆187Updated this week
- A safetensors extension to efficiently store sparse quantized tensors on disk☆73Updated this week
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆331Updated 6 months ago
- KernelBench: Can LLMs Write GPU Kernels? - Benchmark with Torch -> CUDA problems☆166Updated this week
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆192Updated 2 months ago
- Repository for the QUIK project, enabling the use of 4bit kernels for generative inference - EMNLP 2024☆175Updated 10 months ago
- scalable and robust tree-based speculative decoding algorithm☆332Updated 2 weeks ago
- Cataloging released Triton kernels.☆164Updated last month
- ☆175Updated this week
- Efficient LLM Inference over Long Sequences☆356Updated this week
- Experiments on speculative sampling with Llama models☆124Updated last year
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆107Updated 2 months ago
- This repository contains the experimental PyTorch native float8 training UX☆221Updated 6 months ago
- ☆172Updated 4 months ago
- extensible collectives library in triton☆82Updated 4 months ago
- vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs☆88Updated this week
- An efficent implementation of the method proposed in "The Era of 1-bit LLMs"☆154Updated 4 months ago
- [MLSys'24] Atom: Low-bit Quantization for Efficient and Accurate LLM Serving☆293Updated 7 months ago
- Code for Neurips24 paper: QuaRot, an end-to-end 4-bit inference of large language models.☆339Updated 2 months ago
- QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving☆495Updated 3 weeks ago
- ☆67Updated 3 months ago