chatlearn/models/vllm_module.py [388:407]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            if self.worker.gpu_cache is not None:
                for ele in self.worker.gpu_cache: # pylint: disable=unused-variable
                    ele = None
                self.worker.gpu_cache = None # pylint: disable=access-member-before-definition

            if hasattr(self.worker, "cache_engine") and self.worker.cache_engine is not None:
                for c_e in self.worker.cache_engine:
                    c_e.cpu_cache = None
                    c_e.gpu_cache = None
                self.worker.cache_engine = None

        self.clear_cache()

    def clear_cache(self):
        if not self.timers("gc").started_:
            self.timers("gc").start()
        gc.collect()
        self.timers("gc").stop()

        super().empty_cache()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



chatlearn/models/vllm_module_v2.py [515:534]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        if self.worker.gpu_cache is not None:
            for ele in self.worker.gpu_cache: # pylint: disable=unused-variable
                ele = None
            self.worker.gpu_cache = None # pylint: disable=access-member-before-definition

        if hasattr(self.worker, "cache_engine") and self.worker.cache_engine is not None:
            for c_e in self.worker.cache_engine:
                c_e.cpu_cache = None
                c_e.gpu_cache = None
            self.worker.cache_engine = None

        self.clear_cache()

    def clear_cache(self):
        if not self.timers("gc").started_:
            self.timers("gc").start()
        gc.collect()
        self.timers("gc").stop()

        super().empty_cache()
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -