abacusai / gh200-llm
Packages and instructions for training and inference of LLMs on NVIDIA's new GH200 machines
☆19Updated 2 months ago
Related projects ⓘ
Alternatives and complementary repositories for gh200-llm
- A safetensors extension to efficiently store sparse quantized tensors on disk☆50Updated this week
- ring-attention experiments☆97Updated last month
- ☆99Updated last month
- Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters☆104Updated last month
- ☆12Updated last month
- Simple and fast low-bit matmul kernels in CUDA / Triton☆145Updated this week
- 🚀 Efficiently (pre)training foundation models with native PyTorch features, including FSDP for training and SDPA implementation of Flash…☆193Updated this week
- Cold Compress is a hackable, lightweight, and open-source toolkit for creating and benchmarking cache compression methods built on top of…☆87Updated 3 months ago
- extensible collectives library in triton☆72Updated last month
- Collection of kernels written in Triton language☆68Updated 3 weeks ago
- Fast Matrix Multiplications for Lookup Table-Quantized LLMs☆187Updated this week
- Fast Inference of MoE Models with CPU-GPU Orchestration☆172Updated this week
- Applied AI experiments and examples for PyTorch☆166Updated 3 weeks ago
- Code for the paper "QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models".☆262Updated last year
- Benchmark suite for LLMs from Fireworks.ai☆58Updated 2 weeks ago
- Example of applying CUDA graphs to LLaMA-v2☆10Updated last year
- vLLM: A high-throughput and memory-efficient inference and serving engine for LLMs☆89Updated this week
- ☆55Updated 5 months ago
- Cataloging released Triton kernels.☆134Updated 2 months ago
- Official code for "SWARM Parallelism: Training Large Models Can Be Surprisingly Communication-Efficient"☆128Updated 11 months ago
- Make triton easier☆41Updated 5 months ago
- ☆153Updated this week
- 🚀 Collection of components for development, training, tuning, and inference of foundation models leveraging PyTorch native components.☆165Updated this week
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- train with kittens!☆49Updated 3 weeks ago
- ☆35Updated 3 weeks ago
- Repo for "LoLCATs: On Low-Rank Linearizing of Large Language Models"☆177Updated last month
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- This repository contains the experimental PyTorch native float8 training UX☆211Updated 3 months ago
- ☆45Updated 2 weeks ago