Update Flashinfer to 0.2.14.post1 (#23537)

Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: siyuanf <siyuanf@nvidia.com>
Signed-off-by: Weiliang Liu <weiliangl@nvidia.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Siyuan Fu <siyuanf@nvidia.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

vllm/v1/worker/gpu_worker.py

@@ -310,6 +310,10 @@ class Worker(WorkerBase):
             logger.info("Compile and warming up model for size %d", size)
             self.model_runner._dummy_run(size, skip_eplb=True)
 
+        # Warmup and tune the kernels used during model execution before
+        # cuda graph capture.
+        kernel_warmup(self)
+
         if not self.model_config.enforce_eager:
             self.model_runner.capture_model()
 
@@ -334,9 +338,6 @@ class Worker(WorkerBase):
                 self.model_runner._dummy_sampler_run(
                     hidden_states=last_hidden_states)
 
-        # Warmup kernels used during model execution
-        kernel_warmup(self)
-
         # Reset the seed to ensure that the random state is not affected by
         # the model initialization and profiling.
         set_random_seed(self.model_config.seed)