diff --git a/constraints.txt b/constraints.txt
index 25ae35bdecfc..17a66eff2535 100644
--- a/constraints.txt
+++ b/constraints.txt
@@ -8,3 +8,7 @@ wheel>=0.46.2
 protobuf>=6.33.5
 # WAR against https://github.com/advisories/GHSA-6mq8-rvhq-8wgg
 aiohttp>=3.13.3
+# WAR against https://github.com/advisories/GHSA-qjxf-f2mg-c6mc
+tornado>=6.5.5
+# WAR against https://github.com/advisories/GHSA-3936-cmfr-pm3m
+black>=26.3.1
diff --git a/examples/models/core/gemma/requirements.txt b/examples/models/core/gemma/requirements.txt
index 20f8719a379c..a1bbed25b68a 100644
--- a/examples/models/core/gemma/requirements.txt
+++ b/examples/models/core/gemma/requirements.txt
@@ -5,7 +5,6 @@
 nvidia-cudnn-cu12~=8.9; platform_machine == "x86_64"
 tensorrt_llm>=0.0.0.dev0
 flax~=0.8.0
-numpy<2
 # jax[cuda12_pip]~=0.4.19
 safetensors~=0.4.1
 sentencepiece>=0.1.99
diff --git a/requirements-dev.txt b/requirements-dev.txt
index a972122b05aa..1b4a7faf5054 100644
--- a/requirements-dev.txt
+++ b/requirements-dev.txt
@@ -36,5 +36,5 @@ opentelemetry-api>=1.26.0
 opentelemetry-exporter-otlp>=1.26.0
 opentelemetry-semantic-conventions-ai>=0.4.1
 fuzzywuzzy==0.18.0
-aiperf==0.4.0
+aiperf==0.6.0
 nanobind>=2.9.0
diff --git a/requirements.txt b/requirements.txt
index 65d622cd91b3..4d4ab8acea9f 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -7,7 +7,7 @@ cuda-python>=13
 diffusers>=0.27.0
 lark
 mpi4py
-numpy<2
+numpy>=2.0.0,<2.4 # numba 0.63.1 requires numpy<2.4
 onnx>=1.18.0,<1.20.0
 onnx_graphsurgeon>=0.5.2
 openai
@@ -70,7 +70,7 @@ blobfile
 openai-harmony==0.0.4
 nvidia-cutlass-dsl==4.3.4; python_version >= "3.10"
 plotly
-numexpr<2.14.0 # WAR for attempted use of nonexistent numpy.typing
+numexpr
 partial_json_parser
 apache-tvm-ffi==0.1.6 # used for reduce nvidia-cutlass-dsl host overhead
 torch-c-dlpack-ext==0.1.3 # used for reduce nvidia-cutlass-dsl host overhead, optional package for improved torch tensor calling perf