[Bug]: Super V3 NVFP4 server crash when multi stream is enabled
Open
@suyoggupta is already working on this.
Since Apr 16, 2026.
bug
Customized kernels
- Dominant language
- Python
- Stars
- 14.7k
- Forks
- 2.8k
- Avg merge
- 2d 23h
- Merged PRs (30d)
- 489
Description
System Info
B200
Who can help?
No response
Information
- The official example scripts
- My own modified scripts
Tasks
- An officially supported task in the
examplesfolder (such as GLUE/SQuAD, ...) - My own task or dataset (give details below)
Reproduction
bench-sweep --model nvidia/NVIDIA-Nemotron-3-Super-120B-A12B-NVFP4 --config-path examples/auto_deploy/super_v3.yaml --concurrencies "1 4 8 16 32 64 128" --world-size 1 --tag ad_fp4kvfp_tp1 --isl 50000 --osl 2048 --server-type trtllm-autodeploy
Expected behavior
server should run without crashing
actual behavior
server crash with
/opt/pytorch/pytorch/aten/src/ATen/native/cuda/TensorCompare.cu:109: _assert_async_cuda_kernel: block: [0,0,0], thread: [0,0,0] Assertion `` failed.
additional notes
NA
Before submitting a new issue...
- Make sure you already searched for relevant issues, and checked the documentation and examples for answers to frequently asked questions.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.