diff --git a/ATTRIBUTIONS-Python.md b/ATTRIBUTIONS-Python.md
index 7e74b846a85f..4d2111f72cdd 100644
--- a/ATTRIBUTIONS-Python.md
+++ b/ATTRIBUTIONS-Python.md
@@ -5261,7 +5261,7 @@ For more information, please refer to <http://unlicense.org>
   - `Tracker`: https://github.com/tox-dev/py-filelock/issues
 
 
-## flashinfer-python (0.6.15)
+## flashinfer-python (0.6.16)
 
 ### Licenses
 License: `Apache-2.0`
diff --git a/requirements.txt b/requirements.txt
index e592848fc725..d63bc1a93be2 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -58,7 +58,7 @@ ordered-set
 peft>=0.18.1,<0.19.0
 patchelf
 einops
-flashinfer-python==0.6.15
+flashinfer-python==0.6.16
 xgrammar==0.1.32
 llguidance==0.7.29
 jsonschema
diff --git a/security_scanning/poetry.lock b/security_scanning/poetry.lock
index 9a15b72d2e09..da2bcef38b54 100644
--- a/security_scanning/poetry.lock
+++ b/security_scanning/poetry.lock
@@ -1352,14 +1352,14 @@ dev = ["pytest", "pytest-xdist", "ruff"]
 
 [[package]]
 name = "flashinfer-python"
-version = "0.6.15"
+version = "0.6.16"
 description = "FlashInfer: Kernel Library for LLM Serving"
 optional = false
 python-versions = "<4.0,>=3.10"
 groups = ["main"]
 files = [
-    {file = "flashinfer_python-0.6.15-py3-none-any.whl", hash = "sha256:da6c339e14db4831ade0d593324f02907d44bd4b86b640faad4727d9e089477b"},
-    {file = "flashinfer_python-0.6.15.tar.gz", hash = "sha256:2a3f1ed47129f9ac9505a26a8f12cadefc0f27d3104fb623ae281032f49eae5f"},
+    {file = "flashinfer_python-0.6.16-py3-none-any.whl", hash = "sha256:059d629cf352dae2d2e17c9b632f1be7c12fd7feb4979d71cdffd96104219e53"},
+    {file = "flashinfer_python-0.6.16.tar.gz", hash = "sha256:0c89970ee42b0640d3dfd65ea4770710e21101ce2b43a09eda3e29cd1874fe48"},
 ]
 
 [package.dependencies]
@@ -1371,7 +1371,7 @@ einops = "*"
 nccl4py = ">=0.3.1"
 ninja = "*"
 numpy = "*"
-nvidia-cudnn-frontend = ">=1.13.0"
+nvidia-cudnn-frontend = ">=1.25.0"
 nvidia-cutlass-dsl = ">=4.5.0"
 nvidia-ml-py = "*"
 packaging = ">=24.2"
@@ -7166,4 +7166,4 @@ type = ["pytest-mypy (>=1.0.1) ; platform_python_implementation != \"PyPy\""]
 [metadata]
 lock-version = "2.1"
 python-versions = ">=3.10,<3.13"
-content-hash = "545f5614cbddc906d0319c8dfff2466fad1620f8e2c884c761fd6fbfe3723d2d"
+content-hash = "4b44e19a983f42a22e97772e3141d54fc362bc465a51813e4d28398646200574"
diff --git a/security_scanning/pyproject.toml b/security_scanning/pyproject.toml
index d0e1715a0f12..95421dde09bf 100644
--- a/security_scanning/pyproject.toml
+++ b/security_scanning/pyproject.toml
@@ -54,7 +54,7 @@ dependencies = [
     "peft (>=0.18.1,<0.19.0)",
     "patchelf (>=0.17.2.4,<0.18.0.0)",
     "einops (>=0.8.2,<0.9.0)",
-    "flashinfer-python (==0.6.15)",
+    "flashinfer-python (==0.6.16)",
     "xgrammar (==0.1.32)",
     "llguidance (==0.7.29)",
     "jsonschema (>=4.26.0,<5.0.0)",
diff --git a/tensorrt_llm/_torch/attention_backend/fmha/flashinfer_trtllm_gen.py b/tensorrt_llm/_torch/attention_backend/fmha/flashinfer_trtllm_gen.py
index ff2002c36d57..a8c659e8bbc8 100644
--- a/tensorrt_llm/_torch/attention_backend/fmha/flashinfer_trtllm_gen.py
+++ b/tensorrt_llm/_torch/attention_backend/fmha/flashinfer_trtllm_gen.py
@@ -159,6 +159,7 @@ def _trtllm_gen_batch_decode_with_kv_cache(
         None,  # lse
         0,  # lse_stride_tokens
         0,  # lse_stride_heads
+        False,  # enable_block_sparse_attention (added in flashinfer 0.6.16, flashinfer-ai/flashinfer#3955)
     )