[Docs] Add SVG images for pooling models. (#42626)

Signed-off-by: Gracie Guo <[email protected]> Signed-off-by: wang.yuqi <[email protected]> Co-authored-by: Gracie Guo <[email protected]> Co-authored-by: wang.yuqi <[email protected]>
2026-08-16 02:38:12 +00:00 · 2026-05-18 22:50:38 -07:00
parent 27f4ba9481
commit 9fd8487d2f
5 changed files with 2336 additions and 0 deletions
@@ -33,6 +33,12 @@ from large language models, allowing them to benefit from the continuous improve
 similarity enables them to reuse much of vLLM’s infrastructure. If compatible, we would be happy to help them leverage
 the latest features of vLLM as well.

+### Cheat Sheet
+
+As illustrated in the figure below, we have summarized the relationships among the key elements of pooling models as a takeaway.
+
+![Cheat Sheet](../../assets/models/pooling_models/cheat_sheet.svg)
+
 ### Sequence-wise Task and Token-wise Task

 The key distinction between sequence-wise task and token-wise task lies in their output granularity: sequence-wise task
@@ -61,6 +67,8 @@ are a subset of classification models that accept two prompts as input and outpu

 ### Pooling Types

+![Pooling Types](../../assets/models/pooling_models/pooling_types.svg)
+
 | Pooling Tasks  | Granularity   | Description                                                                                                                                                                                       |
 |----------------|---------------|---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
 | `CLS` pooling  | Sequence-wise | For BERT‑like (bidirectional self‑attention) models, CLS pooling is used by default. This means the last_hidden_states corresponding to the first token (the [CLS] token) is taken as the output. |
@@ -71,6 +79,8 @@ are a subset of classification models that accept two prompts as input and outpu

 ### Score Types

+![Score Types](../../assets/models/pooling_models/score_types.svg)
+
 The scoring models is designed to compute similarity scores between two input prompts. It supports three model types
 (aka `score_type`): `cross-encoder`, `late-interaction`, and `bi-encoder`.

@@ -25,6 +25,12 @@ The score models is designed to compute similarity scores between two input prom
 !!! note
    Only when a classification model outputs num_labels equal to 1 can it be used as a scoring model and have its scoring API enabled.

+### Score Types
+
+The three supported scoring functions are as illustrated in the figure below.
+
+![Score Types](../../assets/models/pooling_models/score_types.svg)
+
 ## Supported Models

 ### Cross-encoder models