vllm.v1.attention.backends.utils ¶

def compute_mm_prefix_range_tensor(
    mm_prefix_range: dict[int, list[tuple[int, int]]] | None,
    num_seqs: int,
    device: torch.device,
) -> torch.Tensor | None:
    """Convert mm_prefix_range dict to padded tensor for Triton kernel.

    Returns shape: (num_seqs, max_ranges, 2) with 0-padding for empty ranges.
    Empty ranges have start==end==0, which kernel skips via is_valid check.
    """
    if mm_prefix_range is None:
        return None

    range_lists = [
        mm_prefix_range.get(i, [(0, 0)]) or [(0, 0)] for i in range(num_seqs)
    ]

    if all(r == [(0, 0)] for r in range_lists):
        return None

    max_ranges = max(len(r) for r in range_lists)
    padded = []
    for r in range_lists:
        padded_r = list(r) + [(0, 0)] * (max_ranges - len(r))
        padded.append(padded_r)
    padded = async_tensor_h2d(padded, dtype=torch.int32, device=device)
    return padded.view(num_seqs, max_ranges, 2)

def fill_mm_prefix_query_ranges(
    out: np.ndarray,
    mm_prefix_range: dict[int, list[tuple[int, int]]] | None,
    query_start_loc_cpu: torch.Tensor,
    seq_lens_cpu: torch.Tensor,
) -> int:
    """Map each scheduled query token to the mm_prefix range containing it.

    Writes into ``out``, a caller-owned ``(max_num_batched_tokens, 2)`` int32
    staging buffer, and returns the number of rows written (0 if no range
    covers any scheduled query token, in which case ``out`` is untouched and
    the caller should skip the mask_mod entirely). Row ``i`` holds the absolute
    ``[start, end]`` bounds of the bidirectional range that query token ``i``
    belongs to, or ``(-1, -1)`` when it is outside every range.

    mm_prefix ranges never overlap, so "query and key share a range" is
    equivalent to "the key lies inside the query's own range". The kernel
    therefore needs no key-side lookup, and this metadata is sized by scheduled
    query tokens rather than by context length -- bounded by
    ``max_num_batched_tokens`` instead of ``num_seqs * max_seq_len``.

    Ranges are absolute prompt positions and may extend past the tokens
    scheduled so far under chunked prefill; the portion outside the current
    chunk is simply not recorded. Degenerate ranges (``start >= end``) are
    skipped to match the Triton path's ``start < end`` validity check.

    ``seq_lens_cpu`` only needs to be exact for prefill rows, since mm_prefix
    ranges cover prompt tokens: an over-estimate on a decode row shifts that
    row's query position further past every range, which still matches nothing.
    """
    if mm_prefix_range is None:
        return 0

    query_start_loc = query_start_loc_cpu.numpy()
    num_actual_tokens = int(query_start_loc[-1])
    if num_actual_tokens <= 0:
        return 0
    assert num_actual_tokens <= out.shape[0], (
        f"mm_prefix staging buffer holds {out.shape[0]} tokens, got {num_actual_tokens}"
    )

    # Resolve every span before touching `out`, so batches whose ranges all
    # fall outside the scheduled tokens skip the fill entirely.
    spans: list[tuple[int, int, int, int]] = []
    for req_idx, req_ranges in mm_prefix_range.items():
        if not req_ranges:
            continue
        token_start = int(query_start_loc[req_idx])
        query_len = int(query_start_loc[req_idx + 1]) - token_start
        if query_len <= 0:
            continue
        # Absolute position of this request's first scheduled query token.
        context_len = int(seq_lens_cpu[req_idx]) - query_len
        for start, end in req_ranges:
            if start >= end:
                continue
            first = max(start - context_len, 0)
            last = min(end - context_len, query_len - 1)
            if first > last:
                continue
            spans.append((token_start + first, token_start + last + 1, start, end))

    if not spans:
        return 0

    out[:num_actual_tokens] = -1
    for row_start, row_end, start, end in spans:
        out[row_start:row_end] = (start, end)
    return num_actual_tokens

def get_dcp_local_seq_lens(
    seq_lens: torch.Tensor,
    dcp_size: int = 1,
    dcp_rank: int | None = None,
    cp_kv_cache_interleave_size: int = 1,
) -> torch.Tensor:
    """While using dcp, kv_cache size stored on each rank may be different,
    use this function to calculate split decode seq_lens of each dcp rank.
    Only consider dcp now, we can extend the case of cp based on this.
    """
    seq_lens_i32 = seq_lens.to(torch.int32)
    if dcp_rank is None:
        rank_offsets = torch.arange(
            dcp_size,
            dtype=torch.int32,
            device=seq_lens.device,
        ).view(
            *((1,) * seq_lens_i32.dim()),
            dcp_size,
        )
        seq_lens_tiled = seq_lens_i32.unsqueeze(-1)
    else:
        rank_offsets = torch.tensor(dcp_rank, dtype=torch.int32, device=seq_lens.device)
        seq_lens_tiled = seq_lens_i32
    base = (
        seq_lens_tiled
        // cp_kv_cache_interleave_size
        // dcp_size
        * cp_kv_cache_interleave_size
    )
    remainder = seq_lens_tiled - base * dcp_size
    remainder = torch.clip(
        remainder - rank_offsets * cp_kv_cache_interleave_size,
        0,
        cp_kv_cache_interleave_size,
    )
    dcp_local_seq_lens = base + remainder
    return dcp_local_seq_lens

def get_flashinfer_layout_string(layout: KVCacheLayout) -> str:
    """Return the layout name in FlashInfer's convention (NHD/HND)."""
    assert layout.name in _FLASHINFER_LAYOUT_NAMES, (
        f"KV cache layout {layout.name} has no FlashInfer equivalent; FlashInfer "
        "rejects it in supported_kv_cache_layouts"
    )
    return _FLASHINFER_LAYOUT_NAMES[layout.name]

def get_num_attention_heads_from_layers(
    vllm_config: VllmConfig, layer_names: list[str]
) -> int | None:
    """Per-TP-rank ``num_heads`` shared by the named Attention layers.

    Use in metadata builders whose plan-time allocations depend on the
    head count: the model-wide ``get_num_attention_heads()`` is wrong
    for models with non-uniform per-layer head counts. All layers in
    one attention group must agree on ``num_heads``; this is asserted.
    Returns ``None`` when no matching Attention layer is found.
    """
    attn_layers = get_layers_from_vllm_config(
        vllm_config,
        AttentionLayerBase,  # type: ignore[type-abstract]
        layer_names,
    )
    if not attn_layers:
        return None
    heads = {layer.impl.num_heads for layer in attn_layers.values()}
    assert len(heads) == 1, (
        f"All layers in one attention group must share num_heads; "
        f"got {heads} for {layer_names}."
    )
    return heads.pop()

def get_per_layer_parameters(
    vllm_config: VllmConfig, layer_names: list[str], cls_: type["AttentionImpl"]
) -> dict[str, PerLayerParameters]:
    """
    Scan layers in `layer_names` and determine some hyperparameters
    to use during `plan`.
    """

    layers = get_layers_from_vllm_config(
        vllm_config,
        AttentionLayerBase,  # type: ignore[type-abstract]
        layer_names,
    )
    per_layer_params: dict[str, PerLayerParameters] = {}

    for key, layer in layers.items():
        impl = layer.impl
        assert isinstance(impl, cls_)

        # Infer hyperparameters from the attention layer
        window_size = getattr(impl, "sliding_window", None)
        window_left = window_size[0] if window_size is not None else -1
        logits_soft_cap = getattr(impl, "logits_soft_cap", None)
        sm_scale = impl.scale
        has_sinks = getattr(impl, "sinks", None) is not None

        per_layer_params[key] = PerLayerParameters(
            window_left, logits_soft_cap, sm_scale, has_sinks
        )

    return per_layer_params

def get_supported_kv_cache_layouts(
    backends: Iterable[type[AttentionBackend]],
) -> list[KVCacheLayout]:
    """Layouts every one of the worker's backends supports, most preferred first.

    Every backend declares the layouts its kernels support, most preferred first
    (``supported_kv_cache_layouts``), or None when any layout works; workers where
    nothing declares follow the default preference. Identical declarations keep
    their order; otherwise the layout the most backends put first wins, ties
    keeping the enum order. An empty intersection is a hard error.
    """
    supported_layouts_lists: list[Sequence[KVCacheLayout]] = [
        layouts
        for backend in backends
        if (layouts := backend.supported_kv_cache_layouts()) is not None
    ] or [_DEFAULT_LAYOUT_PREFERENCE]

    first = supported_layouts_lists[0]
    if all(layouts == first for layouts in supported_layouts_lists[1:]):
        return list(first)

    priorities: dict[KVCacheLayout, int] = defaultdict(int)
    for preferred_layout, *_ in supported_layouts_lists:
        priorities[preferred_layout] += 1
    supported_layouts = set.intersection(*map(set, supported_layouts_lists))
    candidates = sorted(
        (layout for layout in KVCacheLayout if layout in supported_layouts),
        key=lambda layout: priorities[layout],
        reverse=True,
    )
    if not candidates:
        raise ValueError(
            "No KV cache layout satisfies every supported set: "
            f"{list(map(_layout_names, supported_layouts_lists))}."
        )
    return candidates

def infer_global_hyperparameters(
    per_layer_params: dict[str, PerLayerParameters],
) -> PerLayerParameters:
    """
    Currently, FlashInfer backend other than trtllm-gen
    only support models in which all layers share
    the same values for the following hyperparameters:
    - `window_left`
    - `logits_soft_cap`
    - `sm_scale`

    So this function asserts that all layers share the same values for these
    hyperparameters and returns the global values.
    """

    assert len(per_layer_params) > 0, "No attention layers found in the model."

    param_sets = list(per_layer_params.values())
    global_params = param_sets[0]

    global_params.has_same_window_lefts = all(
        params.window_left == global_params.window_left for params in param_sets
    )
    global_params.has_same_all_params = all(
        params == global_params for params in param_sets
    )

    return global_params

def log2_lse_to_ln(lse: torch.Tensor) -> torch.Tensor:
    """Convert a base-2 log-sum-exp tensor to natural-log units."""
    return lse * _LN_2

def mamba_get_block_table_tensor(
    block_table: torch.Tensor,
    seq_lens: torch.Tensor,
    kv_cache_spec: KVCacheSpec,
    mamba_cache_mode: str,
) -> torch.Tensor:
    """
    Get the block table tensor for mamba kernels from the input
    common_attn_metadata.block_table_tensor given different mamba cache modes.

    - "all":   input  (#requests, cdiv(max_model_len, block_size)
                        + num_speculative_blocks);
               output (#requests, cdiv(max_model_len, block_size)
                        + num_speculative_blocks).

    - "none":  input  (#requests, 1 + num_speculative_blocks);
               output (#requests, 1 + num_speculative_blocks).

    - "align": input  (#requests, cdiv(max_model_len, block_size));
               output (#requests, 1 + num_speculative_blocks), which are the last
               1 + num_speculative_blocks of each request.
    """
    if mamba_cache_mode in ("all", "none"):
        return block_table
    else:
        assert isinstance(kv_cache_spec, MambaSpec)
        # NOTE: For 0-length requests in CUDA graph, use a start_index of 0
        # to handle the invalid block table.
        start_indices = (seq_lens - 1) // kv_cache_spec.block_size
        start_indices.clamp_(min=0)
        # Use int32 for arithmetic to avoid dtype promotion overhead,
        # then convert to int64 for gather (which requires Long indices)
        offsets = torch.arange(
            1 + kv_cache_spec.num_speculative_blocks,
            device=block_table.device,
            dtype=torch.int32,
        )
        indices_to_gather = (start_indices.unsqueeze(1) + offsets).to(torch.int64)
        return torch.gather(block_table, 1, indices_to_gather)

def record_kv_cache_layout(cache_config: CacheConfig, layout_name: str) -> None:
    """Adopt a layout resolved elsewhere (the engine core) in this process."""
    layout = _layout_from_name(layout_name)
    existing = cache_config.kv_cache_layout
    if existing is not None and existing != layout.name:
        raise ValueError(
            f"KV cache layout is already resolved to {existing}; "
            f"cannot change it to {layout.name}."
        )
    cache_config.kv_cache_layout = layout.name

def reorder_batch_to_split_decodes_and_prefills(
    input_batch: "InputBatch",
    scheduler_output: "SchedulerOutput",
    decode_threshold: int = 1,
) -> bool:
    """
    Reorders the batch to split into prefill and decode requests; places all
    requests with <= decode_threshold tokens at the front of the batch.

    The batch is reordered into 4 regions:
        decode:        (num_scheduled <= threshold AND is not prefilling)
        short_extend:  (num_scheduled <= threshold AND is chunked prefilling)
        long_extend:   (num_scheduled > threshold AND is chunked prefilling)
        prefill:       (num_computed == 0)   # First chunks

    Returns:
        True if the batch was modified, False otherwise.
    """
    num_reqs = len(input_batch.req_ids)
    num_scheduled_tokens = [
        scheduler_output.num_scheduled_tokens[id] for id in input_batch.req_ids
    ]
    num_scheduled_tokens_np = np.array(num_scheduled_tokens)
    num_computed_tokens_np = input_batch.num_computed_tokens_cpu[:num_reqs]
    num_prompt_tokens_np = input_batch.num_prompt_tokens[:num_reqs]

    has_context = num_computed_tokens_np > 0
    is_below_threshold = num_scheduled_tokens_np <= decode_threshold
    done_prefilling = num_computed_tokens_np >= num_prompt_tokens_np

    # Mutually exclusive categories (exactly one True per request):
    # 1. No context yet -> prefill
    # 2. Has context, above threshold -> long_extend
    # 3. Has context, below threshold, still prefilling -> short_extend
    # 4. Has context, below threshold, done prefilling -> decode
    is_pure_prefill = ~has_context
    is_long_extend = has_context & ~is_below_threshold
    is_short_extend = has_context & is_below_threshold & ~done_prefilling
    is_decode = has_context & is_below_threshold & done_prefilling

    # Desired order: decode → short_extend → long_extend → prefill
    req_regions = np.zeros(num_reqs, dtype=np.int32)  # 0 = decode by default
    req_regions[is_short_extend] = 1
    req_regions[is_long_extend] = 2
    req_regions[is_pure_prefill] = 3

    num_decodes = int(is_decode.sum())
    num_short_extends = int(is_short_extend.sum())
    num_long_extends = int(is_long_extend.sum())
    num_prefills = int(is_pure_prefill.sum())

    target_regions = np.repeat(
        [0, 1, 2, 3],
        [num_decodes, num_short_extends, num_long_extends, num_prefills],
    ).astype(np.int32)

    needs_swap = req_regions != target_regions

    if not needs_swap.any():
        return False

    # Extract indices that need swapping and sort by target region
    orig_indices = np.where(needs_swap)[0]
    sorted_order = np.argsort(req_regions[needs_swap], kind="stable")
    src_indices = orig_indices[sorted_order]

    src_dest_map = {int(src): int(dst) for src, dst in zip(src_indices, orig_indices)}

    for src in src_dest_map:
        dst = src_dest_map[src]
        while src != dst:
            input_batch.swap_states(src, dst)
            # Mark dst as done by updating its destination to itself
            next_dst = src_dest_map.get(dst, dst)
            src_dest_map[dst] = dst
            dst = next_dst

    return True

def reshape_attn_output_for_spec_decode(attn_output: torch.Tensor) -> torch.Tensor:
    """
    Reshapes the attention output tensor, so that
    the batch_size and seq_len dimensions are combined.
    """
    if attn_output.dim() == 3:
        # Already in the correct shape
        return attn_output
    assert attn_output.dim() == 4, f"attn_output must be 4D, got {attn_output.dim()}D"
    total_tokens = attn_output.shape[0] * attn_output.shape[1]
    return attn_output.view(total_tokens, attn_output.shape[2], attn_output.shape[3])

def reshape_query_for_spec_decode(query: torch.Tensor, batch_size: int) -> torch.Tensor:
    """
    Reshapes the query tensor for the specified batch size, so that
    it has shape (batch_size, seq_len, num_heads, head_dim).
    """
    assert query.dim() == 3, f"query must be 3D, got {query.dim()}D"
    total_tokens = query.shape[0]
    num_heads = query.shape[1]
    head_dim = query.shape[2]
    assert total_tokens % batch_size == 0, (
        f"{total_tokens=} is not divisible by {batch_size=}"
    )
    seq_len = total_tokens // batch_size
    return query.view(batch_size, seq_len, num_heads, head_dim)

def resolve_kv_cache_layout(
    vllm_config: VllmConfig,
    supported_layouts: list[list[str]],
    kv_cache_specs: Iterable[KVCacheSpec] | None = None,
) -> KVCacheLayout:
    """Resolve one KV cache layout for the whole model.

    Runs once in the engine core. Every worker reports the layouts its backends
    support, most preferred first (``get_supported_kv_cache_layouts``); all
    ranks run the same backends, so their lists must agree. Specs mixing HNC
    shapes narrow the candidates to block-compact layouts. An explicit
    ``VLLM_KV_CACHE_LAYOUT`` must be one of the candidates or resolution fails,
    with the legacy ``NHD``/``HND`` names as aliases for ``LBNHC``/``LBHNC``; the
    connector's preference is used when compatible and dropped with a warning
    otherwise. A layout already present on ``cache_config`` wins outright, and
    the result is recorded there (see ``CacheConfig.kv_cache_layout``); it
    reaches workers through the ``set_kv_cache_layout`` RPC and
    ``KVCacheConfig.kv_cache_layout``.
    """
    cache_config = vllm_config.cache_config
    if cache_config.kv_cache_layout is not None:
        return cache_config.get_resolved_kv_cache_layout()

    assert supported_layouts and all(supported_layouts), (
        "No worker reported supported KV cache layouts."
    )
    assert all(names == supported_layouts[0] for names in supported_layouts[1:]), (
        f"Workers disagree on supported KV cache layouts: {supported_layouts}."
    )
    candidates = [_layout_from_name(name) for name in supported_layouts[0]]

    # A block-compact layout means the block is densely packed in memory, so any mix of
    # specs can re-interpret HNC with different sizes as long as the total number of
    # bytes is the same. If not block-compact, each spec must agree on HNC to alias
    # the same page (this aliasing is done by the Hybrid Memory Allocator, HMA).
    hnc_shapes = {
        (spec.num_heads, spec.num_states, spec.page_size_bytes)
        for spec in kv_cache_specs or ()
    }
    if len(hnc_shapes) > 1:
        candidates = [m for m in candidates if m.is_block_compact]
        if not candidates:
            raise ValueError(
                "Specs with mixed HNC shapes need a block-compact layout, but "
                f"none is in every supported set: {supported_layouts}."
            )

    if (requested := envs.VLLM_KV_CACHE_LAYOUT) is not None:
        layout = _layout_from_name(requested)
        if layout not in candidates:
            raise ValueError(
                f"VLLM_KV_CACHE_LAYOUT={requested} does not satisfy every "
                f"supported set; valid layouts: {_layout_names(candidates)}."
            )
    elif (connector := get_kv_connector_cache_layout(vllm_config)) is not None:
        layout = _layout_from_name(connector)
        if layout not in candidates:
            logger.warning_once(
                f"KV connector cache layout {connector} does not satisfy every "
                f"supported set; valid layouts: {_layout_names(candidates)}. "
                f"Using {candidates[0].name} instead."
            )
            layout = candidates[0]
    else:
        layout = candidates[0]

    logger.info_once("Using %s KV cache layout.", layout.name)
    cache_config.kv_cache_layout = layout.name
    return layout

def split_decodes_and_prefills(
    common_attn_metadata: CommonAttentionMetadata,
    decode_threshold: int = 1,
    require_uniform: bool = False,
    treat_short_extends_as_decodes: bool = True,
) -> tuple[int, int, int, int]:
    """
    Assuming a reordered batch, finds the boundary between prefill and decode
    requests.

    The batch is expected to be ordered as:
        decode → short_extend → long_extend → prefill

    Args:
        common_attn_metadata: CommonAttentionMetadata object containing the
            batch metadata.
        decode_threshold: The maximum query length to be considered a decode.
        require_uniform: If True, requires that all decode requests have the
            same query length. When set, some queries may be considered prefills
            even if they are <= decode_threshold, in order to ensure uniformity.
        treat_short_extends_as_decodes: If True (default), short extends
            (query_len <= threshold but still prefilling) are counted as
            decodes. If False, they are counted as prefills.

    Returns:
        num_decodes: The number of decode requests.
        num_prefills: The number of prefill requests.
        num_decode_tokens: The number of tokens in the decode requests.
        num_prefill_tokens: The number of tokens in the prefill requests.
    """
    max_query_len = common_attn_metadata.max_query_len
    num_reqs = common_attn_metadata.num_reqs
    num_tokens = common_attn_metadata.num_actual_tokens
    query_start_loc = common_attn_metadata.query_start_loc_cpu

    if (
        max_query_len <= decode_threshold
        and (not require_uniform or decode_threshold <= 1)
        and treat_short_extends_as_decodes
    ):
        return num_reqs, 0, num_tokens, 0

    query_lens = query_start_loc[1:] - query_start_loc[:-1]
    if query_lens[0].item() > decode_threshold:
        # first request is not decode, so no decode requests
        return 0, num_reqs, 0, num_tokens

    if require_uniform:
        # check if we are in a padded uniform batch; this is used for full-CGs, some
        # requests may have a query length of 0 but since they are padding its fine
        # to treat them as decodes (ensures num_decodes matches the captured size)
        if treat_short_extends_as_decodes and torch.all(
            (query_lens == query_lens[0]) | (query_lens == 0)
        ):
            return num_reqs, 0, num_tokens, 0  # all decodes
        is_prefill = query_lens != query_lens[0]
    else:
        is_prefill = query_lens > decode_threshold

    if not treat_short_extends_as_decodes:
        assert common_attn_metadata.is_prefilling is not None
        is_prefill |= common_attn_metadata.is_prefilling

    if not torch.any(is_prefill):
        return num_reqs, 0, num_tokens, 0

    first_prefill = is_prefill.int().argmax(dim=-1).item()
    num_decodes = first_prefill
    num_prefills = num_reqs - num_decodes
    num_decode_tokens = query_start_loc[first_prefill].item()
    num_prefill_tokens = num_tokens - num_decode_tokens
    return (num_decodes, num_prefills, num_decode_tokens, num_prefill_tokens)

def split_decodes_prefills_and_extends(
    common_attn_metadata: CommonAttentionMetadata,
    decode_threshold: int = 1,
) -> tuple[int, int, int, int, int, int]:
    """
    Assuming a reordered batch, finds the boundary between prefill and decode
    requests.

    Args:
        common_attn_metadata: CommonAttentionMetadata object containing the
            batch metadata.
        decode_threshold: The maximum query length to be considered a decode.

    Returns:
        num_decodes: The number of decode requests.
        num_extends: The number of extend requests.
        num_prefills: The number of prefill requests.
        num_decode_tokens: The number of tokens in the decode requests.
        num_extend_tokens: The number of tokens in the extend requests.
        num_prefill_tokens: The number of tokens in the prefill requests.
    """
    max_query_len = common_attn_metadata.max_query_len
    num_reqs = common_attn_metadata.num_reqs
    num_tokens = common_attn_metadata.num_actual_tokens
    query_start_loc = common_attn_metadata.query_start_loc_cpu

    if max_query_len <= decode_threshold:
        return num_reqs, 0, 0, num_tokens, 0, 0

    # Upper bound is exact for prefill rows; decode rows still satisfy
    # seq_len > query_len under the optimistic bound, so `seq_lens ==
    # query_lens` identifies prefills correctly either way.
    assert common_attn_metadata.seq_lens_cpu_upper_bound is not None
    seq_lens = common_attn_metadata.seq_lens_cpu_upper_bound

    query_lens = query_start_loc[1:] - query_start_loc[:-1]
    is_prefill_or_extend = query_lens > decode_threshold
    is_prefill = (seq_lens == query_lens) & is_prefill_or_extend
    first_extend = is_prefill_or_extend.int().argmax(dim=-1).item()
    first_prefill = is_prefill.int().argmax(dim=-1).item()
    num_decodes = first_extend
    num_decode_tokens = query_start_loc[first_extend].item()
    if not torch.any(is_prefill_or_extend):
        return (num_decodes, 0, 0, num_decode_tokens, 0, 0)

    num_prefills_or_extends = num_reqs - num_decodes
    num_prefill_or_extend_tokens = num_tokens - num_decode_tokens
    if not torch.any(is_prefill):
        return (
            num_decodes,
            num_prefills_or_extends,
            0,
            num_decode_tokens,
            num_prefill_or_extend_tokens,
            0,
        )

    num_extends = first_prefill - num_decodes
    num_prefills = num_reqs - first_prefill

    num_prefill_tokens = num_tokens - query_start_loc[first_prefill]
    num_extend_tokens = num_prefill_or_extend_tokens - num_prefill_tokens
    return (
        num_decodes,
        num_extends,
        num_prefills,
        num_decode_tokens,
        num_extend_tokens,
        num_prefill_tokens,
    )

def split_prefill_chunks(
    seq_lens_cpu: torch.Tensor, workspace_size: int, request_offset: int = 0
) -> list[tuple[int, int]]:
    """
    Split the prefill requests into chunks such that the total sequence length
    of each chunk is less than or equal to the workspace size.

    Args:
        seq_lens_cpu: The sequence lengths of the prefill requests on CPU.
        workspace_size: The maximum workspace size (in tokens) per chunk.
        request_offset: The offset to add to the request indices.
    Returns:
        A list of tuples of (reqs_start, reqs_end) representing chunk boundaries.
    """
    chunk_bounds = []
    i, n = 0, len(seq_lens_cpu)
    assert torch.all(seq_lens_cpu <= workspace_size).item()

    while i < n:
        start, chunk_total = i, 0
        while i < n and (chunk_total + (s := seq_lens_cpu[i].item())) <= workspace_size:
            chunk_total += s
            i += 1
        chunk_bounds.append((start + request_offset, i + request_offset))
    return chunk_bounds

def subclass_attention_metadata(
    name_prefix: str,
    metadata_cls: Any,
    fields: list[tuple[str, Any, Any]],
) -> Any:
    """
    Return a new subclass of `metadata_cls` with additional fields
    """
    name: str = name_prefix + metadata_cls.__name__  # type: ignore
    Wrapped = make_dataclass(name, fields, bases=(metadata_cls,))
    return Wrapped