[Core][Multimodal] Track encode cache entries by mm_hash and enable embedding sharing between requests (#22711)

Signed-off-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: knlnguyen1802 <knlnguyen1802@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>

tests/v1/worker/test_gpu_input_batch.py

@@ -205,6 +205,7 @@ def _construct_cached_request_state(req_id_suffix: int):
         pooling_params=None,
         mm_kwargs=[],
         mm_positions=[],
+        mm_hashes=[],
         block_ids=([], ),
         generator=None,
         num_computed_tokens=len(output_token_ids),