kanshan/TensorRT-LLMs
1
0
Fork 0
mirror of https://github.com/NVIDIA/TensorRT-LLM.git synced 2026-02-04 18:21:52 +08:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

[TRTLLM-5366][chore] Add dgx-spark beta notes (#10766)

Browse Source 
Signed-off-by: Faraz Khoubsirat <58580514+farazkh80@users.noreply.github.com>
Signed-off-by: Wangshanshan <30051912+dominicshanshan@users.noreply.github.com>
This commit is contained in:
Faraz 2026-01-16 19:48:47 -05:00 committed by Yanchao Lu
parent f02948d956
commit aa410c57bc
1 changed files with 16 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

16
docs/source/release-notes.md
View File

@ -8,6 +8,20 @@ All published functionality in the Release Notes has been fully tested and verif
### Key Features and Enhancements
- **DGX Spark Support (Beta)**
- Added beta support for single-node DGX Spark.
- Validated models and precision formats:
- GPT-OSS-20B, GPT-OSS-120B (MXFP4)
- Llama-3.1-8B-Instruct (FP16/FP8/NVFP4)
- Llama-3.3-70B-Instruct (FP8/NVFP4)
- Qwen3-8B, Qwen3-14B (FP16/FP8/NVFP4)
- Qwen3-32B (FP16/NVFP4)
- Qwen3-30B-A3B (FP16/NVFP4)
- NVIDIA-Nemotron-Nano-9B-v2 (FP4)
- Llama-3.3-Nemotron-Super-49B-v1.5 (FP8)
- Phi-4-multimodal-instruct (FP16/FP8/NVFP4)
- Phi-4-reasoning-plus (FP16/FP8/NVFP4)
### Infrastructure Changes
### API Changes
@ -16,6 +30,8 @@ All published functionality in the Release Notes has been fully tested and verif
### Known Issues
- **DGX Spark:** DGX Spark support is in beta. Only single-node configurations and the models listed above have been validated in this release.
## TensorRT-LLM Release 1.1
### Key Features and Enhancements