nvidia-t4

Here are 2 public repositories matching this topic...

dangkhoa2016 / Muse-Glimmer-30B-GGUF-DFlash2-Kaggle-GPU-T4x2

Self-hosted llama.cpp serving stack for Muse-Glimmer-30B GGUF with DFlash2 speculative decoding on Kaggle NVIDIA T4x2 and an authenticated OpenAI-compatible API gateway.

cuda self-hosted kaggle multi-gpu llama-cpp llm-inference gguf speculative-decoding openai-compatible nvidia-t4 dflash2 muse-glimmer-30b

Updated Sep 6, 2026
Python

dangkhoa2016 / KerasHub-TranslateGemma-4B-IT-Kaggle-GPU-T4x2-Text-Vision

Star

Run TranslateGemma 4B IT on Kaggle GPU T4×2 with KerasHub + JAX. Dual-GPU workers, text + vision translation, sync/async REST API, JAX compilation cache, generation bucketing, adaptive startup, benchmarks, tests, and reproducible Kaggle workflow.

translation rest-api machine-translation keras kaggle keras-models text-translation multi-gpu image-translation multimodal vision-language-model translategemma translategemma-4b-it kerashub nvidia-t4

Updated Aug 11, 2026
Python

Add this topic to your repo

To associate your repository with the nvidia-t4 topic, visit your repo's landing page and select "manage topics."

Learn more