| 1 | # SPDX-License-Identifier: Apache-2.0 |
| 2 | # SPDX-FileCopyrightText: Copyright contributors to the vLLM project |
| 3 | |
| 4 | DynamicSDSchedule = list[tuple[int, int, int]] |
| 5 | |
| 6 | |
| 7 | def validate_and_normalize_dynamic_sd_schedule( |
| 8 | num_speculative_tokens_per_batch_size: object, |
| 9 | ) -> DynamicSDSchedule: |
| 10 | """Validate and normalize a Dynamic SD batch-size schedule. |
| 11 | |
| 12 | The schedule is expressed as a list of inclusive ranges: |
| 13 | |
| 14 | ``[(range_start, range_end, num_speculative_tokens), ...]`` |
| 15 | """ |
| 16 | if num_speculative_tokens_per_batch_size is None: |
| 17 | raise ValueError( |
| 18 | "num_speculative_tokens_per_batch_size is required for " |
| 19 | "dynamic speculative decoding." |
| 20 | ) |
| 21 | if not isinstance(num_speculative_tokens_per_batch_size, list): |
| 22 | raise ValueError( |
| 23 | "num_speculative_tokens_per_batch_size must be a non-empty list of " |
| 24 | "(range_start, range_end, num_speculative_tokens) entries." |
| 25 | ) |
| 26 | if not num_speculative_tokens_per_batch_size: |
| 27 | raise ValueError("num_speculative_tokens_per_batch_size must not be empty.") |
| 28 | |
| 29 | parsed_schedule: DynamicSDSchedule = [] |
| 30 | for entry in num_speculative_tokens_per_batch_size: |
| 31 | if not isinstance(entry, list | tuple) or len(entry) != 3: |
| 32 | raise ValueError( |
| 33 | "Each num_speculative_tokens_per_batch_size entry must be a " |
| 34 | "3-item sequence: (range_start, range_end, num_speculative_tokens)." |
| 35 | ) |
| 36 | |
| 37 | range_start, range_end, num_speculative_tokens = ( |
| 38 | int(entry[0]), |
| 39 | int(entry[1]), |
| 40 | int(entry[2]), |
| 41 | ) |
| 42 | |
| 43 | if range_start <= 0 or range_end <= 0: |
| 44 | raise ValueError( |
| 45 | f"Batch-size range ({range_start}, {range_end}) must be positive." |
| 46 | ) |
| 47 | if range_start > range_end: |
| 48 | raise ValueError( |
| 49 | "Batch-size range start must be <= end for " |
| 50 | f"({range_start}, {range_end}, {num_speculative_tokens})." |
| 51 | ) |
| 52 | if num_speculative_tokens < 0: |
| 53 | raise ValueError( |
| 54 | "num_speculative_tokens_per_batch_size values must be >= 0." |
| 55 | ) |
| 56 | |
| 57 | parsed_schedule.append((range_start, range_end, num_speculative_tokens)) |
| 58 | |
| 59 | parsed_schedule.sort(key=lambda entry: entry[0]) |
| 60 | |
| 61 | previous_end = 0 |
| 62 | for range_start, range_end, _ in parsed_schedule: |
| 63 | if range_start <= previous_end: |
| 64 | raise ValueError("Batch-size ranges must be non-overlapping and sorted.") |
| 65 | previous_end = range_end |
| 66 | |
| 67 | first_range_start = parsed_schedule[0][0] |
| 68 | if first_range_start != 1: |
| 69 | raise ValueError( |
| 70 | "The first batch-size range must start at 1 so every runtime " |
| 71 | "batch size has a defined schedule." |
| 72 | ) |
| 73 | |
| 74 | return parsed_schedule |
| 75 | |
| 76 | |
| 77 | def build_dynamic_sd_schedule_lookup( |
| 78 | num_speculative_tokens_per_batch_size: object, |
| 79 | vllm_max_batch_size: int, |
| 80 | vllm_num_speculative_tokens: int, |
| 81 | ) -> list[int]: |
| 82 | """Expand the configured schedule into a dense batch_size -> K lookup. |
| 83 | |
| 84 | "dense_schedule" means a 1-indexed lookup table where index ``batch_size`` |
| 85 | stores the exact K to use for that runtime batch size. This lets the |
| 86 | scheduler do a simple array lookup instead of searching the configured |
| 87 | ranges on every scheduling step. |
| 88 | """ |
| 89 | if vllm_max_batch_size <= 0: |
| 90 | raise ValueError("vllm_max_batch_size must be > 0.") |
| 91 | if vllm_num_speculative_tokens <= 0: |
| 92 | raise ValueError("vllm_num_speculative_tokens must be > 0.") |
| 93 | |
| 94 | parsed_schedule = validate_and_normalize_dynamic_sd_schedule( |
| 95 | num_speculative_tokens_per_batch_size |
| 96 | ) |
| 97 | |
| 98 | # Index 0 is intentionally unused so that valid runtime batch sizes can be |
| 99 | # looked up directly as dense_schedule[batch_size]. |
| 100 | dense_schedule = [0] * (vllm_max_batch_size + 1) |
| 101 | next_batch_size = 1 |
| 102 | last_num_speculative_tokens: int | None = None |
| 103 | |
| 104 | for range_start, range_end, num_speculative_tokens in parsed_schedule: |
| 105 | if range_start > next_batch_size and last_num_speculative_tokens is not None: |
| 106 | # Fill any gap before the next configured range by carrying forward |
| 107 | # the previous K. For example, [(1, 16, 3), (32, 128, 2)] should map |
| 108 | # batch sizes 17-31 to K=3. |
| 109 | for batch_size in range( |
| 110 | next_batch_size, |
| 111 | min(range_start, vllm_max_batch_size + 1), |
| 112 | ): |
| 113 | dense_schedule[batch_size] = min( |
| 114 | vllm_num_speculative_tokens, |
| 115 | last_num_speculative_tokens, |
| 116 | ) |
| 117 | |
| 118 | # Fill the current configured inclusive range with its K value. |
| 119 | for batch_size in range( |
| 120 | max(range_start, next_batch_size), |
| 121 | min(range_end, vllm_max_batch_size) + 1, |
| 122 | ): |
| 123 | dense_schedule[batch_size] = min( |
| 124 | vllm_num_speculative_tokens, |
| 125 | num_speculative_tokens, |
| 126 | ) |
| 127 | |
| 128 | next_batch_size = max(next_batch_size, range_end + 1) |
| 129 | last_num_speculative_tokens = num_speculative_tokens |
| 130 | |
| 131 | if next_batch_size > vllm_max_batch_size: |
| 132 | break |
| 133 | |
| 134 | if last_num_speculative_tokens is None: |
| 135 | raise ValueError( |
| 136 | "num_speculative_tokens_per_batch_size must contain at least " |
| 137 | "one valid batch-size range." |
| 138 | ) |
| 139 | |
| 140 | # Fill the tail after the final configured range by carrying forward the |
| 141 | # last K through vllm_max_batch_size. |
| 142 | for batch_size in range(next_batch_size, vllm_max_batch_size + 1): |
| 143 | dense_schedule[batch_size] = min( |
| 144 | vllm_num_speculative_tokens, |
| 145 | last_num_speculative_tokens, |
| 146 | ) |
| 147 | |
| 148 | return dense_schedule |