From 95cfe102a5ffd6bc10c2e897a2d3f3fd3fb250db Mon Sep 17 00:00:00 2001 From: "Li, Jiang" Date: Fri, 15 May 2026 18:58:19 +0800 Subject: [PATCH] [Bugfix] Ensure embeding model compilation on CPU (#42709) Signed-off-by: jiang1.li --- vllm/v1/worker/cpu_worker.py | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/vllm/v1/worker/cpu_worker.py b/vllm/v1/worker/cpu_worker.py index 72503ab9ab7..1474d7ecb7a 100644 --- a/vllm/v1/worker/cpu_worker.py +++ b/vllm/v1/worker/cpu_worker.py @@ -213,10 +213,13 @@ class CPUWorker(Worker): return kv_cache_size def compile_or_warm_up_model(self) -> CompilationTimes: + # Note: the model has been compiled in determine_available_memory(), + # Only compile here for models without kv cache + if len(self.model_runner.kv_caches) == 0: + self.model_runner.warming_up_model() # 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) - # Note: the model has been compiled in determine_available_memory() return CompilationTimes( language_model=self.compilation_config.compilation_time, encoder=self.compilation_config.encoder_compilation_time,