Michaelvll / llm-ie-benchmarksLinks
A collection of reproducible inference engine benchmarks
☆31Updated last month
Alternatives and similar repositories for llm-ie-benchmarks
Users that are interested in llm-ie-benchmarks are comparing it to the libraries listed below
Sorting:
- Make triton easier☆47Updated 11 months ago
- Some microbenchmarks and design docs before commencement☆12Updated 4 years ago
- Using FlexAttention to compute attention with different masking patterns☆43Updated 8 months ago
- Benchmark for machine learning model online serving (LLM, embedding, Stable-Diffusion, Whisper)☆28Updated last year
- ☆27Updated last month
- Compression for Foundation Models☆31Updated 2 months ago
- A place to store reusable transformer components of my own creation or found on the interwebs☆56Updated 3 weeks ago
- JaxPP is a library for JAX that enables flexible MPMD pipeline parallelism for large-scale LLM training☆45Updated 2 weeks ago
- Repository for Sparse Finetuning of LLMs via modified version of the MosaicML llmfoundry☆42Updated last year
- [WIP] Better (FP8) attention for Hopper☆30Updated 3 months ago
- NAACL '24 (Best Demo Paper RunnerUp) / MlSys @ NeurIPS '23 - RedCoast: A Lightweight Tool to Automate Distributed Training and Inference☆66Updated 5 months ago
- ☆33Updated last month
- ☆21Updated 3 months ago
- FlexAttention w/ FlashAttention3 Support☆26Updated 8 months ago
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆115Updated last week
- DPO, but faster 🚀☆42Updated 5 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆69Updated 11 months ago
- ☆70Updated 2 weeks ago
- ☆46Updated 11 months ago
- ☆15Updated 2 months ago
- WIP. Veloce is a low-code Ray-based parallelization library that makes machine learning computation novel, efficient, and heterogeneous.☆18Updated 2 years ago
- [ICLR2025] Breaking Throughput-Latency Trade-off for Long Sequences with Speculative Decoding☆116Updated 6 months ago
- [ACL 2024] RelayAttention for Efficient Large Language Model Serving with Long System Prompts☆39Updated last year
- Cray-LM unified training and inference stack.☆22Updated 4 months ago
- ☆45Updated 3 months ago
- Demo of the unit_scaling library, showing how a model can be easily adapted to train in FP8.☆44Updated 10 months ago
- Benchmark suite for LLMs from Fireworks.ai☆75Updated 3 weeks ago
- Boosting 4-bit inference kernels with 2:4 Sparsity☆75Updated 9 months ago
- Vocabulary Parallelism☆19Updated 2 months ago
- Utilities for Training Very Large Models☆58Updated 8 months ago