tensorchord / inference-benchmarkLinks
Benchmark for machine learning model online serving (LLM, embedding, Stable-Diffusion, Whisper)
☆28Updated last year
Alternatives and similar repositories for inference-benchmark
Users that are interested in inference-benchmark are comparing it to the libraries listed below
Sorting:
- A collection of reproducible inference engine benchmarks☆31Updated 2 months ago
- Some microbenchmarks and design docs before commencement☆12Updated 4 years ago
- WIP. Veloce is a low-code Ray-based parallelization library that makes machine learning computation novel, efficient, and heterogeneous.☆18Updated 2 years ago
- Sentence Embedding as a Service☆15Updated last year
- Manages vllm-nccl dependency☆17Updated last year
- Make triton easier☆46Updated last year
- Benchmark suite for LLMs from Fireworks.ai☆76Updated 2 weeks ago
- Open sourced backend for Martian's LLM Inference Provider Leaderboard☆18Updated 10 months ago
- ☆15Updated 2 months ago
- ☆28Updated 2 months ago
- ☆54Updated 7 months ago
- ☆34Updated last month
- Distributed ML Optimizer☆32Updated 3 years ago
- vLLM adapter for a TGIS-compatible gRPC server.☆32Updated this week
- DPO, but faster 🚀☆43Updated 6 months ago
- The backend behind the LLM-Perf Leaderboard☆10Updated last year
- ☆119Updated last year
- Distributed IO-aware Attention algorithm☆20Updated 10 months ago
- Repository for CPU Kernel Generation for LLM Inference☆26Updated last year
- Simple dependency injection framework for Python☆21Updated last year
- ☆36Updated this week
- Blazing fast data loading with HuggingFace Dataset and Ray Data☆16Updated last year
- ☆86Updated 2 months ago
- Odysseus: Playground of LLM Sequence Parallelism☆70Updated last year
- [ICML 2023] SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models☆11Updated last year
- ☆39Updated 2 years ago
- Fast LLM Training CodeBase With dynamic strategy choosing [Deepspeed+Megatron+FlashAttention+CudaFusionKernel+Compiler];☆38Updated last year
- A place to store reusable transformer components of my own creation or found on the interwebs☆56Updated this week
- A Ray-based data loader with per-epoch shuffling and configurable pipelining, for shuffling and loading training data for distributed tra…☆18Updated 2 years ago
- [EMNLP 2023 Industry Track] A simple prompting approach that enables the LLMs to run inference in batches.☆74Updated last year