apple / ml-recurrent-drafterLinks
☆217Updated 7 months 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
Sorting:
- scalable and robust tree-based speculative decoding algorithm☆355Updated 6 months ago
- Fast low-bit matmul kernels in Triton☆349Updated this week
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆277Updated last year
- A high-throughput and memory-efficient inference and serving engine for LLMs☆266Updated 10 months ago
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆260Updated last month
- KV cache compression for high-throughput LLM inference☆134Updated 6 months ago
- A safetensors extension to efficiently store sparse quantized tensors on disk☆149Updated last week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆208Updated last week
- ArcticInference: vLLM plugin for high-throughput, low-latency inference☆210Updated last week
- ArcticTraining is a framework designed to simplify and accelerate the post-training process for large language models (LLMs)☆200Updated last week
- ring-attention experiments☆149Updated 10 months ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆80Updated 11 months ago
- Code for data-aware compression of DeepSeek models☆43Updated 2 months ago
- Efficient LLM Inference over Long Sequences☆389Updated last month
- [ICLR'25] Fast Inference of MoE Models with CPU-GPU Orchestration☆226Updated 9 months ago
- ☆80Updated last month
- Applied AI experiments and examples for PyTorch☆290Updated 2 months ago
- Load compute kernels from the Hub☆244Updated this week
- Triton-based implementation of Sparse Mixture of Experts.☆233Updated 8 months ago
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆128Updated 8 months ago
- Fault tolerance for PyTorch (HSDP, LocalSGD, DiLoCo, Streaming DiLoCo)☆383Updated last week
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆141Updated last year
- Official implementation for Training LLMs with MXFP4☆75Updated 3 months ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆124Updated 8 months ago
- Experiments on speculative sampling with Llama models☆128Updated 2 years ago
- [NeurIPS 2024] KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization☆372Updated last year
- Code for paper: "QuIP: 2-Bit Quantization of Large Language Models With Guarantees"☆377Updated last year
- Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024☆327Updated 3 months ago
- This repository contains the experimental PyTorch native float8 training UX☆224Updated last year
- Benchmark suite for LLMs from Fireworks.ai☆79Updated 3 weeks ago