diff --git a/cpp/tensorrt_llm/kernels/fmhaDispatcher.cpp b/cpp/tensorrt_llm/kernels/fmhaDispatcher.cpp
index 0676e4487249..3d1ffa741f67 100644
--- a/cpp/tensorrt_llm/kernels/fmhaDispatcher.cpp
+++ b/cpp/tensorrt_llm/kernels/fmhaDispatcher.cpp
@@ -49,10 +49,10 @@ QkvLayout AttentionInputLayoutToQkvLayout(AttentionInputLayout layout)
 
 FmhaDispatcher::FmhaDispatcher(MHARunnerFixedParams fixedParams)
     : mFixedParams(fixedParams)
-    // TRTLLM-GEN only supports power of 2 head sizes.
+    // TRTLLM-GEN only supports power of 2 head sizes (and 80 with padding).
     // The exception will fall back to fmha v2.
     // Please update fmha_v2/setup.py if you want to add more supported head sizes.
-    , mUseTllmGen(tensorrt_llm::common::isSM100Family() && fixedParams.headSize != 80 && fixedParams.headSize != 72)
+    , mUseTllmGen(tensorrt_llm::common::isSM100Family() && fixedParams.headSize != 72)
 {
     if (mUseTllmGen)
     {
diff --git a/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/kernelMetaInfo.h b/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/kernelMetaInfo.h
index d6a9814b66dd..e2a4c4fe52bd 100644
--- a/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/kernelMetaInfo.h
+++ b/cpp/tensorrt_llm/kernels/trtllmGenKernels/fmha/cubin/kernelMetaInfo.h
@@ -24,7 +24,7 @@ namespace kernels
 {
 // clang-format off
 
-#define TLLM_GEN_VERSION "3977eaf5-dirty"
+#define TLLM_GEN_VERSION "09fbb2db-dirty"
 #ifndef EXCLUDE_SM_100
 extern unsigned char const FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128PersistentContext_cubin[];
 extern unsigned char const FmhaSm100aKernel_QE4m3KvE2m1OE4m3H128PagedKvCausalP32VarSeqQ128Kv128StaticContext_cubin[];
diff --git a/tests/unittest/trt/attention/test_gpt_attention.py b/tests/unittest/trt/attention/test_gpt_attention.py
index 61a2f8d26e31..49fadcef77dd 100644
--- a/tests/unittest/trt/attention/test_gpt_attention.py
+++ b/tests/unittest/trt/attention/test_gpt_attention.py
@@ -316,7 +316,7 @@ def load_test_cases():
                 [2],  # batch_size
                 [165],  # in_len
                 [2, 8, 32],  # num_q_heads
-                [32, 64, 96, 128, 160],  # head_size
+                [32, 64, 80, 96, 128, 160],  # head_size
                 [2],  # num_kv_heads
                 [False],
                 [1, 2, 4],  # beam_width
diff --git a/tests/unittest/utils/util.py b/tests/unittest/utils/util.py
index 5bfbd0fff0e0..4a2b2bb435d2 100644
--- a/tests/unittest/utils/util.py
+++ b/tests/unittest/utils/util.py
@@ -157,10 +157,10 @@ def skip_fp8_pre_ada(use_fp8):
 
 
 def skip_blackwell_for_fmha_tests(context_fmha_type, head_size):
-    if (isSM100Family()) and (head_size not in [32, 64, 128] and
+    if (isSM100Family()) and (head_size not in [32, 64, 80, 128] and
                               context_fmha_type != ContextFMHAType.disabled):
         pytest.skip(
-            "Context FMHA only supports head sizes [32, 64, 128] currently on blackwell."
+            "Context FMHA only supports head sizes [32, 64, 80, 128] currently on blackwell."
         )