We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
There was an error while loading. Please reload this page.
1 parent b006b37 commit 950000cCopy full SHA for 950000c
CHANGELOG.md
@@ -2,6 +2,13 @@
2
3
* [NeMo Export-Deploy Release](https://github.com/NVIDIA-NeMo/Export-Deploy/releases)
4
5
+## NVIDIA NeMo-Export-Deploy 0.2.1
6
+* Bug fixes for HuggingFace model deployment (#459)
7
+ - Fixed HuggingFace deployable implementations for both Triton and Ray Serve backends
8
+ - Improved tokenizer handling in HuggingFace deployment scripts
9
+* Minor fixes for Ray deployment (#464)
10
+ - Additional bug fixes in Ray deployment utilities
11
+
12
## NVIDIA NeMo-Export-Deploy 0.2.0
13
* MegatronLM and Megatron-Bridge model deployment support with Triton Inference Server and Ray Serve
14
* Multi-node multi-instance Ray Serve based deployment for NeMo 2, Megatron-Bridge, and Megatron-LM models.
0 commit comments