[VLM] Generalized prompt updates for multi-modal processor (#13964)

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

docs/source/contributing/model/multimodal.md

@@ -720,13 +720,13 @@ def _get_mm_fields_config(
 
 :::::
 
-### Prompt replacements
+### Prompt updates
 
-Override {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_replacements` to
-return a list of {class}`~vllm.multimodal.processing.PromptReplacement` instances.
+Override {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates` to
+return a list of {class}`~vllm.multimodal.processing.PromptUpdate` instances.
 
-Each {class}`~vllm.multimodal.processing.PromptReplacement` instance specifies a find-and-replace
-operation performed by the HF processor.
+Each {class}`~vllm.multimodal.processing.PromptUpdate` instance specifies an update operation
+(e.g.: insertion, replacement) performed by the HF processor.
 
 ::::{tab-set}
 :::{tab-item} Basic example: LLaVA
@@ -743,15 +743,15 @@ for sample in text:
 ```
 
 It simply repeats each input `image_token` a number of times equal to the number of placeholder feature tokens (`num_image_tokens`).
-Based on this, we override {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_replacements` as follows:
+Based on this, we override {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates` as follows:
 
 ```python
-def _get_prompt_replacements(
+def _get_prompt_updates(
     self,
     mm_items: MultiModalDataItems,
     hf_processor_mm_kwargs: Mapping[str, object],
     out_mm_kwargs: MultiModalKwargs,
-) -> list[PromptReplacement]:
+) -> Sequence[PromptUpdate]:
     hf_config = self.info.get_hf_config()
     image_token_id = hf_config.image_token_index
 
@@ -859,7 +859,7 @@ prompt_tokens, prompts_length = _tokenize_prompts_with_image_and_batch(
 )
 ```
 
-To accommodate this, instead of a string you can return an instance of `PromptReplacementDetails`
+To accommodate this, instead of a string you can return an instance of `PromptUpdateDetails`
 with different `full` and `feature` attributes:
 
 ```python
@@ -878,7 +878,7 @@ def get_replacement_fuyu(item_idx: int):
     image_tokens = ([_IMAGE_TOKEN_ID] * ncols +
                     [_NEWLINE_TOKEN_ID]) * nrows
 
-    return PromptReplacementDetails(
+    return PromptUpdateDetails(
         full=image_tokens + [bos_token_id],
         features=image_tokens,
     )
@@ -888,12 +888,12 @@ Finally, noticing that the HF processor removes the `|ENDOFTEXT|` token from the
 we can search for it to conduct the replacement at the start of the string:
 
 ```python
-def _get_prompt_replacements(
+def _get_prompt_updates(
     self,
     mm_items: MultiModalDataItems,
     hf_processor_mm_kwargs: Mapping[str, object],
     out_mm_kwargs: MultiModalKwargs,
-) -> list[PromptReplacement]:
+) -> Sequence[PromptUpdate]:
     hf_config = self.info.get_hf_config()
     bos_token_id = hf_config.bos_token_id
     assert isinstance(bos_token_id, int)
@@ -913,7 +913,7 @@ def _get_prompt_replacements(
         image_tokens = ([_IMAGE_TOKEN_ID] * ncols +
                         [_NEWLINE_TOKEN_ID]) * nrows
 
-        return PromptReplacementDetails(
+        return PromptUpdateDetails(
             full=image_tokens + [bos_token_id],
             features=image_tokens,
         )

docs/source/design/mm_processing.md

@@ -6,11 +6,16 @@ To enable various optimizations in vLLM such as [chunked prefill](#chunked-prefi
 
 Here are the main features of {class}`~vllm.multimodal.processing.BaseMultiModalProcessor`:
 
-## Prompt Replacement Detection
+## Prompt Update Detection
 
-One of the main responsibilies of HF processor is to replace input placeholder tokens (e.g. `<image>` for a single image) with feature placeholder tokens (e.g. `<image><image>...<image>`, the number of which equals to the feature size). The information about which tokens have been replaced is key to finding the correspondence between placeholder feature tokens and multi-modal inputs.
+One of the main responsibilies of HF processor is to update the prompt with placeholder tokens. For example:
 
-In vLLM, this information is specified using {class}`~vllm.multimodal.processing.PromptReplacement` in {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_replacements`. Given this specification, we can automatically detect whether HF has replaced the input placeholder tokens by checking whether the feature placeholder tokens exist in the prompt.
+- Insert feature placeholder tokens (e.g. `<image><image>...<image>`, the number of which equals to the feature size) at the start of the string.
+- Replace existing input placeholder tokens (e.g. `<image>` for a single image) with feature placeholder tokens (e.g. `<image><image>...<image>`, the number of which equals to the feature size).
+
+The information about which tokens have been updated is key to finding the correspondence between placeholder feature tokens and multi-modal inputs.
+
+In vLLM, this information is specified using {class}`~vllm.multimodal.processing.PromptUpdate` in {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates`. We can automatically detect whether HF has updated the prompt by checking the existence of the updated tokens.
 
 ## Tokenized Prompt Inputs
 
@@ -22,7 +27,7 @@ Consider that HF processors follow these main steps:
 
 1. Tokenize the text
 2. Process multi-modal inputs
-3. Perform prompt replacement
+3. Perform prompt updates
 
 And we require that:
 
@@ -44,16 +49,16 @@ Moreover, since the tokenized text has not passed through the HF processor, we h
 
 We work around the first issue by requiring each model to define how to generate dummy text based on the number of multi-modal inputs, via {meth}`~vllm.multimodal.profiling.BaseDummyInputsBuilder.get_dummy_processor_inputs`. This lets us generate dummy text corresponding to the multi-modal inputs and input them together to obtain the processed multi-modal data.
 
-(mm-automatic-prompt-replacement)=
+(mm-automatic-prompt-updating)=
 
-### Automatic prompt replacement
+### Automatic prompt updating
 
 We address the second issue by implementing model-agnostic code in
-{meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._apply_prompt_replacements` to automatically replace input placeholder tokens with feature placeholder tokens based on the specification outputted by {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_replacements`.
+{meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._apply_prompt_updates` to automatically update the prompt with feature placeholder tokens based on the specification outputted by {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._get_prompt_updates`.
 
 ### Summary
 
-With the help of dummy text and automatic prompt replacement, our multi-modal processor can finally accept both text and token prompts with multi-modal data. The detailed logic is shown in {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._apply_hf_processor_main`.
+With the help of dummy text and automatic prompt updating, our multi-modal processor can finally accept both text and token prompts with multi-modal data. The detailed logic is shown in {meth}`~vllm.multimodal.processing.BaseMultiModalProcessor._apply_hf_processor_main`.
 
 ## Processor Output Caching
 
@@ -61,4 +66,4 @@ Some HF processors, such as the one for Qwen2-VL, are [very slow](gh-issue:9238)
 
 When new data is passed in, we first check which items are in the cache, and which ones are missing. The missing items are passed into the HF processor in a single batch and cached, before being merged with the existing items in the cache.
 
-Since we only process the missing multi-modal data items, the number of input placeholder tokens no longer corresponds to the number of the multi-modal inputs, so they can't be passed alongside the text prompt to HF processor. Therefore, we process the text and multi-modal inputs separately, using [dummy text](#mm-dummy-text) to avoid HF errors. Since this skips HF's prompt replacement code, we apply [automatic prompt replacement](#mm-automatic-prompt-replacement) afterwards to keep the output tokens and multi-modal data consistent with each other.
+Since we only process the missing multi-modal data items, the number of input placeholder tokens no longer corresponds to the number of the multi-modal inputs, so they can't be passed alongside the text prompt to HF processor. Therefore, we process the text and multi-modal inputs separately, using [dummy text](#mm-dummy-text) to avoid HF errors. Since this skips HF's prompt updating code, we apply [automatic prompt updating](#mm-automatic-prompt-updating) afterwards to keep the output tokens and multi-modal data consistent with each other.