NVIDIA Nemotron
Open-Source Project Brings Nemotron 3.5 to Older GPUs
A community-maintained vLLM fork adds INT8 inference for older AMD and NVIDIA GPUs, including support for Nemotron 3.5 Bolt.
1 article tagged with this topic
A community-maintained vLLM fork adds INT8 inference for older AMD and NVIDIA GPUs, including support for Nemotron 3.5 Bolt.