mirror of
https://github.com/FlashML-org/FreeToken.git
synced 2026-11-21 01:52:30 +08:00
* feat(mm): serve image input on the Qwen VL families - frontend: OpenAI image_url, Anthropic image blocks and Responses input_image (http(s), base64, gated file://) become MMItems in the tokenizer workers; image spans carry content pseudo ids so the radix cache keys them by content; mrope positions are precomputed per request - registry: EncoderSpec per family (Qwen3-VL, Qwen3.6, Qwen3.8-Flash-Next register a vision encoder serving image) and ModelSpec.mm_processor; EngineConfig.active_encoders decides what a process builds, served_modalities what it accepts; --text-model-only, --mm-disable, --mm-encoder-weights, --mm-embed-cache-device, --mm-max-pixels - engine and scheduler: per-request encoder-cache row ownership, chunk planning on the batch (jobs, gather rows, scatter rows), items encoded right before the LM forward and gathered into batch.mm_embeds - models: the Qwen VL vision tower on the text tower's TP layers with DeepStack, block weights streamed from pinned host banks by default, merger outputs parked on the host between blocks; SupportsMultimodal (encode, place_encoder_weights) and a shared embed_input_ids - server: image inputs rejected with a client-facing reason when no vision encoder is served; GET /v1/stats reports model.input_modalities * feat(mm): replace the pixel cap with a token budget and processor kwargs - --image-min-tokens / --image-max-tokens replace --mm-max-pixels; MMProcessor.get_mm_processor_kwargs turns the MultimodalConfig into the processor call's arguments, the default passes mm.processor_kwargs through and Qwen VL converts the budget to pixel areas in size.shortest_edge / longest_edge - --mm-processor-kwargs hands a JSON object to the checkpoint's image processor call, applied after the token budget - MMProcessor is an ABC that owns the model path, the config and the lazily loaded image processor; get_mm_processor returns None when --mm-disable leaves no encoder to serve - the frontend tokenizer, the tokenizer worker and the offline LLM build one processor each and hand it to TokenizeManager, so the tokenize message carries no per-request pixel cap
34 lines
1.1 KiB
Python
34 lines
1.1 KiB
Python
"""Multimodal input handling: pad-id scheme, per-family processors, media fetch, embedding cache."""
|
|
|
|
from __future__ import annotations
|
|
|
|
import torch
|
|
|
|
# image spans become content pseudo ids above every real token id: the radix cache keys them by content and the model finds image rows by id >= MM_PAD_SHIFT_VALUE
|
|
# they are clamped back into the vocab before the embedding lookup; those rows are overwritten anyway
|
|
MM_PAD_SHIFT_VALUE = 1_000_000
|
|
|
|
|
|
def restore_placeholder(input_ids: torch.Tensor, token_id: int) -> torch.Tensor:
|
|
"""input_ids with every content pad id put back to the family's placeholder token."""
|
|
return input_ids.masked_fill(input_ids >= MM_PAD_SHIFT_VALUE, token_id)
|
|
|
|
|
|
def mm_pad_value(item_hash: int) -> int:
|
|
return MM_PAD_SHIFT_VALUE + item_hash % (1 << 30)
|
|
|
|
|
|
def check_mm_pad_shift(vocab_size: int) -> None:
|
|
if vocab_size > MM_PAD_SHIFT_VALUE:
|
|
raise ValueError(
|
|
f"vocab_size ({vocab_size}) exceeds MM_PAD_SHIFT_VALUE ({MM_PAD_SHIFT_VALUE}); "
|
|
"image pseudo-ids would alias real token ids"
|
|
)
|
|
|
|
|
|
__all__ = [
|
|
"MM_PAD_SHIFT_VALUE",
|
|
"check_mm_pad_shift",
|
|
"mm_pad_value",
|
|
]
|