diff --git a/jenkins/L0_Test.groovy b/jenkins/L0_Test.groovy
index 8f246f744287..60c5f724dbf8 100644
--- a/jenkins/L0_Test.groovy
+++ b/jenkins/L0_Test.groovy
@@ -1135,6 +1135,10 @@ def getPytestBaseCommandLine(
         extraInternalEnv += " CBTS_COVERAGE_CONFIG=${coverageConfigFile}"
         extraInternalEnv += " CBTS_MARKER_FILE=${outputPath}/cbts_current_test.txt"
     }
+    // Skip TRTLLM-Gen FMHA JIT warmup for non-performance tests.
+    if (!stageName.contains("-Perf-") && !stageName.contains("-PerfSanity-")) {
+        extraInternalEnv += " TLLM_ENABLE_TRTLLM_GEN_FMHA_JIT_WARMUP=0"
+    }
 
     // Container port allocation environment variables for avoiding port conflicts
     def portEnvVars = ""
diff --git a/tensorrt_llm/_torch/pyexecutor/model_engine.py b/tensorrt_llm/_torch/pyexecutor/model_engine.py
index d83f51a1bbe3..fd97b8620d28 100644
--- a/tensorrt_llm/_torch/pyexecutor/model_engine.py
+++ b/tensorrt_llm/_torch/pyexecutor/model_engine.py
@@ -1280,6 +1280,10 @@ def _run_attention_warmup(self,
         if not issubclass(self.attn_backend.Metadata, TrtllmAttentionMetadata):
             return
 
+        if os.environ.get("TLLM_ENABLE_TRTLLM_GEN_FMHA_JIT_WARMUP", "1") != "1":
+            logger.info("Skipping TRTLLM-Gen FMHA JIT warmup")
+            return
+
         @contextlib.contextmanager
         def trtllm_gen_fmha_jit_warmup():
             previous = self._trtllm_gen_jit_warmup