sarman/dgx-spark-playbooks
1
0
Fork 0
mirror of https://github.com/NVIDIA/dgx-spark-playbooks.git synced 2026-04-26 11:53:53 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

Compare commits

base: sarman:a48b522d43d4387a1693da67266fb17ea3ce5f39
Branches Tags
sarman:main
...
compare: sarman:72f0abd1cf6ec80b102d58175cdc34e3c135acda
Branches Tags
sarman:main

2 Commits
a48b522d43 ... 72f0abd1cf

Author SHA1 Message Date
Ago
72f0abd1cf
Merge f75d5817aa into 8452a1c5b1 2026-04-08 03:10:21 +00:00
agolajko
f75d5817aa nemotron reqs --trust-remote-code for vllm setup 2026-01-26 08:16:23 -08:00
1 changed files with 1 additions and 1 deletions
Show Stats Expand all files Collapse all files

2
nvidia/vllm/README.md
View File

@ -82,7 +82,7 @@ The following models are supported with vLLM on Spark. All listed models are ava
| **Nemotron3-Nano** | FP8 | ✅ | [`nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8`](https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8) |
> [!NOTE]
> The Phi-4-multimodal-instruct models require `--trust-remote-code` when launching vLLM.
> The Phi-4-multimodal-instruct and Nemotron3-Nano models require `--trust-remote-code` when launching vLLM.
> [!NOTE]
> You can use the NVFP4 Quantization documentation to generate your own NVFP4-quantized checkpoints for your favorite models. This enables you to take advantage of the performance and memory benefits of NVFP4 quantization even for models not already published by NVIDIA.