[Feature] Support Paddle-OCR (#4396)

* init

* update code

* fix code style & disable thinking

* adapt for common_engine.update_mm_requests_chunk_size

* use 3d rope

* use flash_attn_unpadded

* opt siglip

* update to be compatible with the latest codebase

* fix typo

* optim OCR performance

* fix bug

* fix bug

* fix bug

* fix bug

* normlize name

* modify xpu rope

* revert logger

* fix bug

* fix bug

* fix bug

* support default_v1

* optim performance

* fix bug

---------

Co-authored-by: root <root@szzj-acg-tge1-fdda9.szzj.baidu.com>
Co-authored-by: zhangyue66 <zhangyue66@baidu.com>

fastdeploy/scheduler/global_scheduler.py

@@ -24,6 +24,7 @@ from typing import Dict, List, Optional, Tuple
 import crcmod
 from redis import ConnectionPool
 
+from fastdeploy import envs
 from fastdeploy.engine.request import Request, RequestOutput
 from fastdeploy.scheduler import utils
 from fastdeploy.scheduler.data import ScheduledRequest, ScheduledResponse
@@ -542,22 +543,23 @@ class GlobalScheduler:
                 remaining_request.append((request_queue_name, serialized_request))
                 continue
 
-            if self.enable_chunked_prefill:
-                if request.prompt_tokens_ids_len > self.long_prefill_token_threshold:
-                    long_partial_requests += 1
-                    if long_partial_requests > self.max_long_partial_prefills:
+            if not envs.FD_ENABLE_MAX_PREFILL:
+                if self.enable_chunked_prefill:
+                    if request.prompt_tokens_ids_len > self.long_prefill_token_threshold:
+                        long_partial_requests += 1
+                        if long_partial_requests > self.max_long_partial_prefills:
+                            remaining_request.append((request_queue_name, serialized_request))
+                            continue
+                    else:
+                        short_partial_requests += 1
+
+                    if short_partial_requests + long_partial_requests > self.max_num_partial_prefills:
                         remaining_request.append((request_queue_name, serialized_request))
                         continue
                 else:
-                    short_partial_requests += 1
-
-                if short_partial_requests + long_partial_requests > self.max_num_partial_prefills:
-                    remaining_request.append((request_queue_name, serialized_request))
-                    continue
-            else:
-                if current_prefill_tokens > max_num_batched_tokens:
-                    remaining_request.append((request_queue_name, serialized_request))
-                    continue
+                    if current_prefill_tokens > max_num_batched_tokens:
+                        remaining_request.append((request_queue_name, serialized_request))
+                        continue
 
             scheduled_requests.append(request)
 

fastdeploy/scheduler/local_scheduler.py

@@ -18,6 +18,7 @@ import threading
 import time
 from typing import Dict, List, Optional, Tuple
 
+from fastdeploy import envs
 from fastdeploy.engine.request import Request, RequestOutput
 from fastdeploy.scheduler.data import ScheduledRequest, ScheduledResponse
 from fastdeploy.utils import scheduler_logger
@@ -258,20 +259,21 @@ class LocalScheduler:
                 if required_total_blocks > available_blocks:
                     break
 
-                if self.enable_chunked_prefill:
-                    if request.prompt_tokens_ids_len > self.long_prefill_token_threshold:
-                        # 长请求
-                        long_partial_requests += 1
-                        if long_partial_requests > self.max_long_partial_prefills:
+                if not envs.FD_ENABLE_MAX_PREFILL:
+                    if self.enable_chunked_prefill:
+                        if request.prompt_tokens_ids_len > self.long_prefill_token_threshold:
+                            # 长请求
+                            long_partial_requests += 1
+                            if long_partial_requests > self.max_long_partial_prefills:
+                                break
+                        else:
+                            short_partial_requests += 1
+
+                        if short_partial_requests + long_partial_requests > self.max_num_partial_prefills:
                             break
                     else:
-                        short_partial_requests += 1
-
-                    if short_partial_requests + long_partial_requests > self.max_num_partial_prefills:
-                        break
-                else:
-                    if current_prefill_tokens > max_num_batched_tokens:
-                        break
+                        if current_prefill_tokens > max_num_batched_tokens:
+                            break
 
                 requests.append(request.raw)
             self.ids_read_cursor += len(requests)