Run python3 dev/update_changelog.py --prev-version 2.1...

Signed-off-by: mlflow-automation <mlflow-automation@users.noreply.github.com>

CHANGELOG.md

@@ -1,5 +1,36 @@
 # CHANGELOG
 
+## 2.12.0 (2024-04-05)
+
+MLflow 2.12.0 includes several major features and improvements
+
+Features:
+
+- [Models] Streaming Langchain model prediction output (#11490, @WeichenXu123)
+- [Deployments] Make DatabricksDeploymentClient support prediction with streaming response (#11580, @WeichenXu123)
+- [Server-infra] Introduce private environment variables for overriding http retries (#11590, @BenWilson2)
+- [Artifacts] Introduce ability to use Filesystem service presigned URLs to upload/download model artifacts (#11534, @artjen)
+- [] Log image optimization (#11404, @jessechancy)
+- [Tracking] Lift the DBR check when logging Delta table to MLflow (#11521, @chenmoneygithub)
+
+Bug fixes:
+
+- [Model Registry] Delete registered model permission upon model deletion (#11601, @B-Step62)
+- [Tracking] [MLflow] fix for importing module multiple times to log model path as chain (#11553, @sunishsheth2009)
+- [Models] Support custom prediction functions in `SklearnModelWrapper` (#11577, @B-Step62)
+- [Deployments] Add middle-of-name truncation to excessively long deployment names for Sagemaker image deployment (#11523, @BenWilson2)
+- [Models] Fix langchain inference (#11485, @WeichenXu123)
+- [Tracking] Fix sampling logic in GetSampledHistoryBulkInterval (#11475, @daniellok-db)
+- [Models] Avoid input example conversion for llm/v1/xxx task in Transformer flavor (#11508, @B-Step62)
+
+Documentation updates:
+
+- [] log table images (#11535, @jessechancy)
+
+Small bug fixes and documentation updates:
+
+#11628, #11620, #11610, #11605, #11604, #11600, #11603, #11598, #11572, #11576, #11555, #11563, #11539, #11532, #11528, #11525, #11514, #11513, #11509, #11457, #11501, #11500, @harupy; #11625, #11574, @daniellok-db; #11588, @jessechancy; #11619, @BenWilson2; #11607, #11581, #11516, #11511, @serena-ruan; #11589, @tlm365; #11566, @brynn-code; #11570, @lababidi; #11529, #11517, #11510, #11489, @B-Step62; #11542, @edwardfeng-db; #11533, @WeichenXu123; #11463, @taranarmo; #11506, @ernestwong-db; #11502, @fzyzcjy; #11494, @sunishsheth2009
+
 ## 2.11.3 (2024-03-21)
 
 MLflow 2.11.3 is a patch release that addresses a security exploit with the Open Source MLflow tracking server and miscellaneous Databricks integration fixes