Compiled engines for running Whisper with TRT LLM for much faster inference.
baseten
company
Verified
AI & ML interests
None defined yet.
Recent Activity
View all activity
Collections
1
models
646
baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-A10G-v0.16.0-TP2
Updated
•
4
baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-A10G-v0.16.0-TP1
Updated
•
4
baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.16.0-TP2
Updated
•
8
baseten/btest-Llama-3.1-8B-Instruct-NVIDIA-H100-80GB-HBM3-v0.16.0-TP1
Updated
•
22
baseten/btest-TinyLlama-1.1B-Chat-v1.0-NVIDIA-A10G-v0.16.0-TP1
Updated
•
23
baseten/smol_llama-101M-GQA
Text Generation
•
Updated
•
6
baseten/embedding-smol_llama-101M-GQA
Updated
•
166
baseten/whisper_trt_medium_NVIDIA_L4_0_13_0_dsingal_test_mi1500_l4_bs16
Updated
baseten/whisper_trt_medium_NVIDIA_L4_0_13_0_dsingal_test_mi1500_l4_bs10
Updated
baseten/whisper_trt_large_v3_turbo_NVIDIA_L4_0_13_0_dsingal_test_mi1500_l4_bs20
Updated