graphcore-research / unit-scaling-demo
Unit Scaling demo and experimentation code
☆16Updated 8 months ago
Related projects ⓘ
Alternatives and complementary repositories for unit-scaling-demo
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆38Updated 10 months ago
- ☆88Updated 2 months ago
- FlexAttention w/ FlashAttention3 Support☆27Updated last month
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆74Updated 5 months ago
- Triton implementation of Flash Attention2.0☆22Updated last year
- ☆24Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆51Updated 2 months ago
- Repository for CPU Kernel Generation for LLM Inference☆25Updated last year
- Odysseus: Playground of LLM Sequence Parallelism☆57Updated 5 months ago
- extensible collectives library in triton☆72Updated last month
- Activation-aware Singular Value Decomposition for Compressing Large Language Models☆49Updated last month
- QuIP quantization☆46Updated 8 months ago
- This repository contains code for the MicroAdam paper.☆12Updated 4 months ago
- ☆22Updated 11 months ago
- Fast Hadamard transform in CUDA, with a PyTorch interface☆111Updated 5 months ago
- GPU operators for sparse tensor operations☆29Updated 8 months ago
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆43Updated last year
- An algorithm for static activation quantization of LLMs☆77Updated 2 weeks ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆34Updated 8 months ago
- ☆44Updated 11 months ago
- ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization☆87Updated last month
- ☆55Updated 5 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆147Updated 4 months ago
- ☆96Updated last month
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models"☆56Updated last month
- Quantized Attention on GPU☆30Updated 2 weeks ago
- ☆47Updated 2 months ago
- Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆79Updated this week
- PyTorch bindings for CUTLASS grouped GEMM.☆53Updated 3 weeks ago