diff --git a/docker/docker-compose.yml b/docker/docker-compose.yml
index dd09884..9449286 100644
--- a/docker/docker-compose.yml
+++ b/docker/docker-compose.yml
@@ -27,6 +27,15 @@ services:
       - "5555:5000"
     networks:
       - cognet
+    
+    # uncomment this only when you have gpu access  
+    #deploy:
+    #  resources:
+    #    reservations:
+    #      devices:
+    #        - driver: nvidia
+    #          device_ids: ['0']
+    #          capabilities: ["gpu", "utility", "compute", "video"]
       
 networks:
   cognet:
diff --git a/envs/env_app b/envs/env_app
index 322f8ec..ee3a7a3 100644
--- a/envs/env_app
+++ b/envs/env_app
@@ -23,7 +23,7 @@ APP_MEDCAT_MODEL_PACK=
 # APP_MODEL_CUI_FILTER_PATH=/cat/models/cui_filter.txt
 
 # NLP processing
-APP_BULK_NPROC=16
+APP_BULK_NPROC=8
 APP_TRAINING_MODE=False
 
 # Flask server config
@@ -31,8 +31,12 @@ SERVER_HOST=0.0.0.0
 SERVER_PORT=5000
 SERVER_WORKERS=1
 SERVER_WORKER_TIMEOUT=300
-SERVER_THREADS=16
+SERVER_THREADS=1
+
+# set the number of torch threads, this should be used ONLY if you are using CPUs and the default image
+# set to -1 or 0 if you are using GPU
+APP_TORCH_THREADS=8
 
 # GPU SETTING
 # CAUTION, use only if you are using the GPU docker image.
-APP_TORCH_THREADS=0
\ No newline at end of file
+APP_CUDA_DEVICE_COUNT=1
\ No newline at end of file
diff --git a/medcat_service/nlp_processor/medcat_processor.py b/medcat_service/nlp_processor/medcat_processor.py
index 6b63eb4..ee5335f 100644
--- a/medcat_service/nlp_processor/medcat_processor.py
+++ b/medcat_service/nlp_processor/medcat_processor.py
@@ -133,7 +133,7 @@ def process_content(self, content):
         if self.DEID_MODE:
             entities = self.cat.get_entities(text)["entities"]
             text = self.cat.deid_text(text, redact=self.DEID_REDACT)
-        else:  
+        else:
             if text is not None and len(text.strip()) > 0:
                 entities = self.cat.get_entities(text)
             else:
@@ -164,24 +164,6 @@ def process_content_bulk(self, content):
         :return: processing result containing documents with extracted annotations, stored as KVPs.
         """
 
-        # process at least 10 docs per thread and don't bother with starting
-        # additional threads when less documents were provided
-        min_doc_per_thread = 10
-        num_slices = max(1, int(len(content) / min_doc_per_thread))
-
-        batch_size = min(300, num_slices)
-
-        if batch_size >= self.bulk_nproc:
-            nproc = self.bulk_nproc
-        else:
-            batch_size = min_doc_per_thread
-            nproc = max(1, num_slices)
-            if len(content) > batch_size * nproc:
-                nproc += 1
-
-        self.log.debug("NPROC:" + str(nproc))
-        self.log.debug("Batch size:" + str(batch_size))
-
         # use generators both to provide input documents and to provide resulting annotations
         # to avoid too many mem-copies
         invalid_doc_ids = []
@@ -195,10 +177,9 @@ def process_content_bulk(self, content):
                 for text_record in content:
                     _text_res.append(self.cat.deid_text(text_record["text"], redact=self.DEID_REDACT))
                 content = [{"text": txt} for txt in _text_res]
-                self.log
             else:
-                ann_res = self.cat.multiprocessing_batch_docs_size(
-                    MedCatProcessor._generate_input_doc(content, invalid_doc_ids), batch_size=batch_size, nproc=nproc)
+                ann_res = self.cat.multiprocessing_batch_char_size(
+                    MedCatProcessor._generate_input_doc(content, invalid_doc_ids), nproc=self.bulk_nproc)
 
         except Exception as e:
             self.log.error(repr(e))
@@ -375,9 +356,9 @@ def _generate_result(self, in_documents, annotations, invalid_doc_idx, additiona
                 out_res.update(additional_info)
             elif self.DEID_MODE:
                 out_res = {"text": in_ct["text"],
-                        "annotations": [],
-                        "success": True,
-                        "timestamp": NlpProcessor._get_timestamp()}
+                           "annotations": [],
+                           "success": True,
+                           "timestamp": NlpProcessor._get_timestamp()}
                 out_res.update(additional_info)
             else:
                 # Don't fetch an annotation set
diff --git a/medcat_service/requirements.txt b/medcat_service/requirements.txt
index 54cfd79..cdd508a 100644
--- a/medcat_service/requirements.txt
+++ b/medcat_service/requirements.txt
@@ -1,9 +1,9 @@
 Flask==3.0.2
-gunicorn==20.1.0
-injector==0.20.1
+gunicorn==22.0.0
+injector==0.21.0
 flask-injector==0.15.0
-medcat==1.10.2
+medcat==1.11.0
 setuptools==65.5.1
-simplejson==3.17.6
-werkzeug==3.0.1
-setuptools_rust==1.6.0
\ No newline at end of file
+simplejson==3.19.2
+werkzeug==3.0.3
+setuptools_rust==1.9.0
\ No newline at end of file