graphcore-research / unit-scaling-demoLinks
Unit Scaling demo and experimentation code
☆16Updated last year
Alternatives and similar repositories for unit-scaling-demo
Users that are interested in unit-scaling-demo are comparing it to the libraries listed below
Sorting:
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- QuIP quantization☆52Updated last year
- Boosting 4-bit inference kernels with 2:4 Sparsity☆76Updated 9 months ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- ☆14Updated 2 months ago
- ☆71Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated 11 months ago
- ☆93Updated last week
- Flexible simulator for mixed precision and format simulation of LLMs and vision transformers.☆50Updated last year
- FlexAttention w/ FlashAttention3 Support☆26Updated 8 months ago
- Make triton easier☆47Updated 11 months ago
- Here we will test various linear attention designs.☆58Updated last year
- ☆73Updated 4 months ago
- Code for "RSQ: Learning from Important Tokens Leads to Better Quantized LLMs"☆17Updated 2 weeks ago
- ACL 2023☆39Updated 2 years ago
- ☆157Updated last year
- 32 times longer context window than vanilla Transformers and up to 4 times longer than memory efficient Transformers.☆48Updated last year
- Quantized Attention on GPU☆44Updated 6 months ago
- Accelerate LLM preference tuning via prefix sharing with a single line of code☆41Updated last month
- Pruner-Zero: Evolving Symbolic Pruning Metric from scratch for LLMs☆82Updated 6 months ago
- Official implementation of "The Sparse Frontier: Sparse Attention Trade-offs in Transformer LLMs"☆32Updated last month
- PyTorch bindings for CUTLASS grouped GEMM.☆93Updated last week
- extensible collectives library in triton☆87Updated 2 months ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- The source code of our work "Prepacking: A Simple Method for Fast Prefilling and Increased Throughput in Large Language Models" [AISTATS …☆59Updated 7 months ago
- Best practices for testing advanced Mixtral, DeepSeek, and Qwen series MoE models using Megatron Core MoE.☆17Updated this week
- Framework to reduce autotune overhead to zero for well known deployments.☆74Updated 3 weeks ago
- ☆71Updated 2 weeks ago
- Awesome Triton Resources☆30Updated last month
- ☆22Updated last year