Back to List
Notice:This resource is provided by a third-party author. Please review the code with AI tools or manually before use to ensure security and compatibility.
PythonARahim3/kaggle-tpu-lab

kaggle-tpu-lab

Frontier-class open models on a free Kaggle TPU v5e-8: GLM-5.3-Flash 320B MoE (~64 tok/s, our own JAX engine) and Qwen3.8-27B bf16 (~130 tok/s), 262k context, prefix caching. Works with Claude Code, Codex, opencode and pi.

63.6/100
506Forks: 64
View on GitHub
Loading report...

Similar Projects

OpenLLM

89

Run any open-source LLMs, such as DeepSeek and Llama, as OpenAI compatible API endpoint in the cloud.

Python12.5K

BentoML

86

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

Python8.9K

VLMEvalKit

82

Open-source evaluation toolkit of large multi-modality models (LMMs), support 220+ LMMs, 80+ benchmarks

Python4.4K

lorax

68

Multi-LoRA inference server that scales to 1000s of fine-tuned LLMs

Python3.8K
Back to List