Skip to content

Pin vllm version #140

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
chrisalexiuk-nvidia merged 5 commits into from
Apr 10, 2026
Merged

Pin vllm version #140

Changes from 2 commits
Commits
Show all changes
5 commits
Select commit Hold shift + click to select a range
9718550
Update vLLM to pinned version 0.18.1
chrisalexiuk-nvidia Apr 9, 2026
c42b570
Update vLLM to pinned version nightly
chrisalexiuk-nvidia Apr 10, 2026
3ce5961
Readd Language For Nightly
chrisalexiuk-nvidia Apr 10, 2026
e5c3f35
Merge branch 'main' into pin-vllm-version
chrisalexiuk-nvidia Apr 10, 2026
c9d73b0
Revert Version to Nightly and Re-Add Nightly language
chrisalexiuk-nvidia Apr 10, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 1 addition & 3 deletions usage-cookbook/Nemotron-3-Super/SparkDeploymentGuide/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Nemotron 3 Super — DGX Spark Deployment Guide

DGX Spark ships a single Grace-Blackwell GPU with 128 GB of unified memory. This guide covers serving Nemotron 3 Super on a single DGX Spark using vLLM (nightly) and TensorRT-LLM.
DGX Spark ships a single Grace-Blackwell GPU with 128 GB of unified memory. This guide covers serving Nemotron 3 Super on a single DGX Spark using vLLM and TensorRT-LLM.
Comment thread
chrisalexiuk-nvidia marked this conversation as resolved.
Outdated

## Architecture Refresher

Expand Down Expand Up @@ -32,8 +32,6 @@ wget https://huggingface.co/nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4/raw/m
vllm/vllm-openai:cu130-nightly
```

MTP + NVFP4 on DGX Spark requires a vLLM nightly build (cu130). The pinned release `0.17.1` does not support this combination on a single-GPU Spark configuration.

### Serve Command

```bash
Expand Down
Loading