text-generation-inference/server/text_generation_server/generator.py [756:789]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        size = len(request_ids)
        max_tokens = size * self.model.config.sequence_length
        return CachedBatch(id=batch_id, request_ids=request_ids, size=size, max_tokens=max_tokens)

    def filter(self, batch_id: int, keep_request_ids: List[int]) -> CachedBatch:
        """Remove requests that are not listed from the specified batch

        Args:
            batch_id (`int`):
                The id of a cached batch.
            request_ids(`List[int]`):
                The list of requests that must be kept.

        Return:
            A `CachedBatch` containing the pending requests.
        """
        keep_slot_ids = [slot.id for slot in self.slots if slot.request_id in keep_request_ids]
        self._clear(keep_slot_ids)
        return self._cached_batch(batch_id, keep_request_ids)

    def clear(self, batch_id: Optional[int] = None):
        """Remove a subset or all requests from the generator"""
        keep_ids = []
        if batch_id is not None:
            keep_ids = [slot.id for slot in self.slots if slot.batch_id != batch_id]
        return self._clear(keep_ids)

    def _clear(self, keep_slot_ids: List):
        for slot in self.slots:
            if slot.state != Slot.State.EMPTY and slot.id not in keep_slot_ids:
                logger.debug(f"Removing slot {slot.id} with request {slot.request_id}")
                slot.clear()

    @classmethod
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



text-generation-inference/server/text_generation_server/jetstream_pt_support/generator.py [613:646]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        size = len(request_ids)
        max_tokens = size * self.model.config.sequence_length
        return CachedBatch(id=batch_id, request_ids=request_ids, size=size, max_tokens=max_tokens)

    def filter(self, batch_id: int, keep_request_ids: List[int]) -> CachedBatch:
        """Remove requests that are not listed from the specified batch

        Args:
            batch_id (`int`):
                The id of a cached batch.
            request_ids(`List[int]`):
                The list of requests that must be kept.

        Return:
            A `CachedBatch` containing the pending requests.
        """
        keep_slot_ids = [slot.id for slot in self.slots if slot.request_id in keep_request_ids]
        self._clear(keep_slot_ids)
        return self._cached_batch(batch_id, keep_request_ids)

    def clear(self, batch_id: Optional[int] = None):
        """Remove a subset or all requests from the generator"""
        keep_ids = []
        if batch_id is not None:
            keep_ids = [slot.id for slot in self.slots if slot.batch_id != batch_id]
        return self._clear(keep_ids)

    def _clear(self, keep_slot_ids: List):
        for slot in self.slots:
            if slot.state != Slot.State.EMPTY and slot.id not in keep_slot_ids:
                logger.debug(f"Removing slot {slot.id} with request {slot.request_id}")
                slot.clear()

    @classmethod
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -