mtmd, server: add "placeholder bitmap" for counting tokens , add */input_tokens API (#23913)

* mtmd: add "placeholder bitmap" for counting tokens w/o preprocessing

* fast path skip preproc for placeholder

* fix build

* correct the api

* add server endpoint + tests

* add object name

* update docs

* add proxy handling

* fix build

* fix audio input path

* use is_placeholder in process_mtmd_prompt()

* nits

* nits (2)

* docs: clarify chat/completions/input_tokens is not official

* fix merge problem

tools/server/tests/unit/test_chat_completion.py

@@ -573,3 +573,19 @@ def test_chat_completions_multiple_choices():
         for choice in res.body["choices"]:
             assert "assistant" == choice["message"]["role"]
             assert choice["finish_reason"] == "length"
+
+
+def test_chat_completions_token_count():
+    global server
+    server.start()
+    # make sure cache can be reused across multiple choices and multiple requests
+    # ref: https://github.com/ggml-org/llama.cpp/pull/18663
+    for _ in range(2):
+        res = server.make_request("POST", "/chat/completions/input_tokens", data={
+            "messages": [
+                {"role": "system", "content": "Book"},
+                {"role": "user", "content": "What is the best book"},
+            ],
+        })
+        assert res.status_code == 200
+        assert res.body["input_tokens"] > 5

tools/server/tests/unit/test_vision_api.py

@@ -98,6 +98,25 @@ def test_vision_chat_completion(prompt, image_url, success, re_content):
         assert res.status_code != 200
 
 
+def test_vision_chat_completion_token_count():
+    global server
+    server.start()
+    res = server.make_request("POST", "/chat/completions/input_tokens", data={
+        "temperature": 0.0,
+        "top_k": 1,
+        "messages": [
+            {"role": "user", "content": [
+                {"type": "text", "text": "What is this:"},
+                {"type": "image_url", "image_url": {
+                    "url": get_img_url("IMG_URL_0"),
+                }},
+            ]},
+        ],
+    })
+    assert res.status_code == 200
+    assert res.body["input_tokens"] > 10
+
+
 @pytest.mark.parametrize(
     "prompt, image_data, success, re_content",
     [