Compiled engines for running Whisper with TRT LLM for much faster inference.
baseten
company
Verified
AI & ML interests
None defined yet.
Collections
1
models
541
baseten/tllama-brit-spec-dec-v1
Updated
baseten/whisper-trt-12-large-v2-sanity-checkpoint
Updated
baseten/btest-bloom-560m-HBM3-5fa9436e-TP1
Updated
•
2
baseten/btest-Mistral-7B-Instruct-v0.3-HBM3-5fa9436e-TP2
Updated
•
4
baseten/btest-Mistral-7B-Instruct-v0.3-HBM3-5fa9436e-TP1
Updated
•
4
baseten/btest-Meta-Llama-3.1-8B-Instruct-spec-dec-NVIDIA-H100-80GB-HBM3-v0.12.0-TP2
Updated
•
7
baseten/btest-Meta-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.12.0-TP2
Updated
•
5
baseten/btest-Meta-Llama-3.1-8B-Instruct-spec-dec-NVIDIA-H100-80GB-HBM3-v0.12.0-TP1
Updated
•
9
baseten/btest-Meta-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.12.0-TP1
Updated
•
10
baseten/btest-TinyLlama_v1.1-spec-dec-NVIDIA-A100-SXM4-80GB-v0.12.0-TP2
Updated
•
3