[Docs] Add Phi-4-reasoning-vision to supported models + examples (#39232)

Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>

docs/models/supported_models.md

@@ -601,6 +601,7 @@ These models primarily accept the [`LLM.generate`](./generative_models.md#llmgen
 | `PaliGemmaForConditionalGeneration` | PaliGemma, PaliGemma 2 | T + I<sup>E</sup> | `google/paligemma-3b-pt-224`, `google/paligemma-3b-mix-224`, `google/paligemma2-3b-ft-docci-448`, etc. | ✅︎ | ✅︎ |
 | `Phi3VForCausalLM` | Phi-3-Vision, Phi-3.5-Vision | T + I<sup>E+</sup> | `microsoft/Phi-3-vision-128k-instruct`, `microsoft/Phi-3.5-vision-instruct`, etc. | | ✅︎ |
 | `Phi4MMForCausalLM` | Phi-4-multimodal | T + I<sup>+</sup> / T + A<sup>+</sup> / I<sup>+</sup> + A<sup>+</sup> | `microsoft/Phi-4-multimodal-instruct`, etc. | ✅︎ | ✅︎ |
+| `Phi4ForCausalLMV` | Phi-4-reasoning-vision | T + I<sup>+</sup> | `microsoft/Phi-4-reasoning-vision-15B`, etc. | | ✅︎ |
 | `PixtralForConditionalGeneration` | Ministral 3 (Mistral format), Mistral 3 (Mistral format), Mistral Large 3 (Mistral format), Pixtral (Mistral format) | T + I<sup>+</sup> | `mistralai/Ministral-3-3B-Instruct-2512`, `mistralai/Mistral-Small-3.1-24B-Instruct-2503`, `mistralai/Mistral-Large-3-675B-Instruct-2512` `mistralai/Pixtral-12B-2409` etc. | ✅︎ | ✅︎ |
 | `QwenVLForConditionalGeneration`<sup>^</sup> | Qwen-VL | T + I<sup>E+</sup> | `Qwen/Qwen-VL`, `Qwen/Qwen-VL-Chat`, etc. | ✅︎ | ✅︎ |
 | `Qwen2AudioForConditionalGeneration` | Qwen2-Audio | T + A<sup>+</sup> | `Qwen/Qwen2-Audio-7B-Instruct` | | ✅︎ |

examples/offline_inference/vision_language.py

@@ -1741,6 +1741,27 @@ def run_phi4mm(questions: list[str], modality: str) -> ModelRequestData:
     )
 
 
+# Phi-4-reasoning-vision
+def run_phi4siglip(questions: list[str], modality: str) -> ModelRequestData:
+    assert modality == "image"
+    model_name = "microsoft/Phi-4-reasoning-vision-15B"
+    prompts = [
+        f"<|user|>\n<image>\n{question}<|end|>\n<|assistant|>\n"
+        for question in questions
+    ]
+    engine_args = EngineArgs(
+        model=model_name,
+        trust_remote_code=True,
+        max_model_len=8192,
+        max_num_seqs=2,
+        limit_mm_per_prompt={modality: 1},
+    )
+    return ModelRequestData(
+        engine_args=engine_args,
+        prompts=prompts,
+    )
+
+
 # Pixtral HF-format
 def run_pixtral_hf(questions: list[str], modality: str) -> ModelRequestData:
     assert modality == "image"
@@ -2222,6 +2243,7 @@ model_example_map = {
     "paligemma2": run_paligemma2,
     "phi3_v": run_phi3v,
     "phi4_mm": run_phi4mm,
+    "phi4_siglip": run_phi4siglip,
     "pixtral_hf": run_pixtral_hf,
     "qwen_vl": run_qwen_vl,
     "qwen2_vl": run_qwen2_vl,

examples/offline_inference/vision_language_multi_image.py

@@ -957,6 +957,24 @@ def load_phi4mm(question: str, image_urls: list[str]) -> ModelRequestData:
     )
 
 
+def load_phi4siglip(question: str, image_urls: list[str]) -> ModelRequestData:
+    model_name = "microsoft/Phi-4-reasoning-vision-15B"
+    placeholders = "\n".join("<image>" for _ in image_urls)
+    prompt = f"<|user|>\n{placeholders}\n{question}<|end|>\n<|assistant|>\n"
+    engine_args = EngineArgs(
+        model=model_name,
+        trust_remote_code=True,
+        max_model_len=8192,
+        max_num_seqs=2,
+        limit_mm_per_prompt={"image": len(image_urls)},
+    )
+    return ModelRequestData(
+        engine_args=engine_args,
+        prompt=prompt,
+        image_data=[fetch_image(url) for url in image_urls],
+    )
+
+
 def load_qwen_vl_chat(question: str, image_urls: list[str]) -> ModelRequestData:
     model_name = "Qwen/Qwen-VL-Chat"
     engine_args = EngineArgs(
@@ -1455,6 +1473,7 @@ model_example_map = {
     "paddleocr_vl": load_paddleocr_vl,
     "phi3_v": load_phi3v,
     "phi4_mm": load_phi4mm,
+    "phi4_siglip": load_phi4siglip,
     "pixtral_hf": load_pixtral_hf,
     "qwen_vl_chat": load_qwen_vl_chat,
     "qwen2_vl": load_qwen2_vl,