Upload 38 files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+main_tp_api_x86 filter=lfs diff=lfs merge=lfs -text
+main_tp_x86 filter=lfs diff=lfs merge=lfs -text

main_tp_api_x86

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d1628c4b204088badd37a3a29a36a5d981c124bb0f74280bc2553836d64153d9
+size 1913024

main_tp_x86

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dc91b50dea818b94e13bc3ef87278c9978a1e78588375775b2c7241945423520
+size 1907088

qwen2.5_7b_tp/model.embed_tokens.weight.bfloat16.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ae605b310cf526d54ba22b27796f44010fe28198cb6e3388efb62e09cc2ac4
+size 1089994752

qwen2.5_7b_tp/qwen2_p128_l0_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb50bee841d4f2c40f1d10deb3cb0ec6986eef37ea87e9977f30e06827383ba4
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l10_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd7416274ea6254b7829bdeda162cab365941685030feb3c86fec7ec09506d55
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l11_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f305680487cbc9b9bd517ca56e1512a5cecbed502d46788734a6829ece31f96e
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l12_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c6c5c2d0ead509055e6642d9ff6663e20a4eb53c4ca2950f0f837ad15ca23cc
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l13_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c9cc5a453b3eba8cf13b7f76fd97ca36585a6eeced75488e02fed1905fe1ce1
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l14_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:200907feee14e27d100da7a63b2687383e7966f4416989e09c59d0ff20059642
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l15_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57c264ca8e460c90abf284d9f5883c722e4722144dbcf86d81d1396b8d49ec7d
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l16_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7bc99af71e56f868ba0edc878a2f4c5f7192a523866a4562a8595cddcfb3b16c
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l17_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7120983258195e25d2587ef5e57d2374d7faf589e8161ced554e7550f00fccfb
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l18_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9d5d36d2cd001ca9e4e8d9fcca5a0bae227d91a935e140a10ff524a77665a65
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l19_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e335a4479e40f28006ef214faa2cccae042819e0bc11d3c07e83fe8967d6f82
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l1_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d43e509b0e8fd806cf08853775d46598c0bbaa20b92c102da1cefe57bce3cd09
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l20_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:479bfb707ed0824c6f3238604a45695ca758294b2f58d208c5573554ba9b933e
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l21_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e612b41db2d938e15a74c0f7614e228980ba0cee8a46af6f43f088fbd609823
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l22_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d77d5206886bb932395c94da7b222d9ff6413ffadcc8ae31b81672622e1f1b4
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l23_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8df5f95091162790f958d912b5388d22edc56463074d0f109629037b9fa9b1ce
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l24_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bfc0d7f800a8a89a4c1181af034f6e6abb8ce1045a807e608db2ada41a86db1e
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l25_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:078517c585357c7cdc00629282f4131e3f546024a7f47d14fbe1c8528f0b6814
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l26_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd2ec02d1011168763b6921a72b34df86336b470ad39d08c5f40f64f7fb2f28f
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l27_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9a81c327748f08c12c50be8f3a514739bc23011dc488a949414fefad3e7cf462
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l2_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:080fb080648f7cfa405169474011dde3961fb3a595eecd6db464053987334d80
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l3_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:22b29fad3e093d465612b307c61f3459e659b6dfc07285b3c95ee8f8ede3b237
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l4_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5cf8b8b98472b3b0822a8d7d5b94d206b38fd5d63c2ea35f79c1312ea8e197d8
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l5_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be4e10afb41a504ff1fa07200e0b5f197f70695a2e06c71fed3076c42138315
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l6_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:62924b4766657248d79b19c0bf93410e14eaf2e904a9a6569fded7a8a558a775
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l7_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7cb84548faaac00205d0fc71907c709a4238aab50db40d1f35c469c21960d013
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l8_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5835511951ab1107c28073a76da850bbe66b4092f7d593c699a362b8bba23de
+size 302888960

qwen2.5_7b_tp/qwen2_p128_l9_together.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b59a28e5353f9e6b6ef3a045c27a6926175212b01ab6c54ed2e8b5113b9a02
+size 302888960

qwen2.5_7b_tp/qwen2_post.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08f605137deadfe376e02efb9412277aaf1b5e096114b92b4422484aef866d57
+size 593192960

qwen2.5_tokenizer/tokenizer_config.json

@@ -0,0 +1,207 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null,
+  "add_bos_token": false
+}

qwen2.5_tokenizer_uid.py

@@ -0,0 +1,199 @@
+from transformers import AutoTokenizer, PreTrainedTokenizerFast
+from http.server import HTTPServer, BaseHTTPRequestHandler
+import json
+import argparse
+import uuid
+
+# 全局字典：存储 uid 到 Tokenizer_Http 实例的映射
+tokenizers = {}
+
+class Tokenizer_Http():
+    def __init__(self):
+        model_id = "qwen2.5_tokenizer"
+        self.tokenizer = AutoTokenizer.from_pretrained(model_id)
+        self.messages = [
+            {"role": "system", "content": "You are Qwen, created by Alibaba Cloud. You are a helpful assistant."},
+        ]
+        self.token_ids = []
+        
+        self.token_ids_cache = []
+
+    def encode(self, prompt, last_reply=None):
+        if last_reply is not None:
+            self.messages.append({"role": "assistant", "content": last_reply})
+            text = self.tokenizer.apply_chat_template(
+                self.messages,
+                tokenize=False,
+                add_generation_prompt=True
+            )
+            # print("生成的文本:\n============\n", text, "============\n")
+            self.token_ids = self.tokenizer.encode(text)[:-3]
+        self.messages.append({"role": "user", "content": prompt})
+        
+        text = self.tokenizer.apply_chat_template(
+            self.messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        print("生成的文本:\n============\n", text, "============\n")
+        token_ids = self.tokenizer.encode(text)
+        # 找出新增部分
+        diff = token_ids[len(self.token_ids):]
+        self.token_ids = token_ids
+        print(self.decode(diff))
+        return token_ids, diff
+
+    def decode(self, token_ids):
+        self.token_ids_cache += token_ids
+        text = self.tokenizer.decode(self.token_ids_cache)
+        if "\ufffd" in text and len(self.token_ids_cache) < 9:
+            print("text 中包含非法字符")
+            return ""
+        else:
+            self.token_ids_cache.clear()
+            return text.replace("\ufffd","")
+        
+
+    @property
+    def bos_id(self):
+        return self.tokenizer.bos_token_id
+
+    @property
+    def eos_id(self):
+        return self.tokenizer.eos_token_id
+    
+    @property
+    def bos_token(self):
+        return self.tokenizer.bos_token
+
+    @property
+    def eos_token(self):
+        return self.tokenizer.eos_token
+    
+    def reset(self, system_prompt="You are Qwen, created by Alibaba Cloud. You are a helpful assistant."):
+        self.messages = [
+            {"role": "system", "content": system_prompt},
+        ]
+        text = self.tokenizer.apply_chat_template(
+            self.messages,
+            tokenize=False,
+            add_generation_prompt=True
+        )
+        token_ids = self.tokenizer.encode(text)[:-3]
+        self.token_ids = token_ids
+        print(self.decode(token_ids))
+        return token_ids
+        
+
+class Request(BaseHTTPRequestHandler):
+    timeout = 5
+    server_version = 'Apache'
+
+    def do_GET(self):
+        print("GET 请求路径:", self.path)
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+
+        # 新增接口：获取 uid
+        if '/get_uid' in self.path:
+            new_uid = str(uuid.uuid4())
+            print("新 uid:", new_uid)
+            # 为该 uid 创建一个新的 Tokenizer_Http 实例
+            tokenizers[new_uid] = Tokenizer_Http()
+            msg = json.dumps({'uid': new_uid})
+        elif '/bos_id' in self.path:
+            # 获取 uid 参数（例如 ?uid=xxx）
+            uid = self.get_query_param("uid")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                bos_id = instance.bos_id
+                msg = json.dumps({'bos_id': bos_id if bos_id is not None else -1})
+        elif '/eos_id' in self.path:
+            uid = self.get_query_param("uid")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                eos_id = instance.eos_id
+                msg = json.dumps({'eos_id': eos_id if eos_id is not None else -1})
+        else:
+            msg = json.dumps({'error': 'Invalid GET endpoint'})
+
+        print("响应消息:", msg)
+        self.wfile.write(msg.encode())
+
+    def do_POST(self):
+        content_length = int(self.headers.get('content-length', 0))
+        data = self.rfile.read(content_length).decode()
+        print("POST 请求路径:", self.path)
+        print("接收到的数据:", data)
+        req = json.loads(data)
+
+        self.send_response(200)
+        self.send_header("Content-Type", "application/json")
+        self.end_headers()
+
+        if '/encode' in self.path:
+            # 请求数据中必须包含 uid, text, 和可选的 last_reply
+            uid = req.get('uid')
+            prompt = req.get('text')
+            last_reply = req.get('last_reply')
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                token_ids, diff = instance.encode(prompt, last_reply)
+                msg = json.dumps({'token_ids': token_ids, 'diff': diff})
+        elif '/decode' in self.path:
+            uid = req.get('uid')
+            token_ids = req.get('token_ids')
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                text = instance.decode(token_ids)
+                msg = json.dumps({'text': text})
+        elif '/reset' in self.path:
+            uid = req.get("uid")
+            system_prompt = req.get("system_prompt")
+            instance: Tokenizer_Http = tokenizers.get(uid)
+            if instance is None:
+                msg = json.dumps({'error': 'Invalid uid'})
+            else:
+                if system_prompt is not None:
+                    print("system_prompt:", system_prompt)
+                    token_ids = instance.reset(system_prompt)
+                    msg = json.dumps({'token_ids': token_ids})
+                else:
+                    token_ids = instance.reset()
+                    msg = json.dumps({'token_ids': token_ids})
+        else:
+            msg = json.dumps({'error': 'Invalid POST endpoint'})
+
+        print("响应消息:", msg)
+        self.wfile.write(msg.encode())
+
+    def get_query_param(self, key):
+        """
+        辅助函数：从 GET 请求的 URL 中获取查询参数的值
+        例如：/bos_id?uid=xxx
+        """
+        from urllib.parse import urlparse, parse_qs
+        query = urlparse(self.path).query
+        params = parse_qs(query)
+        values = params.get(key)
+        return values[0] if values else None
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--host', type=str, default='0.0.0.0')
+    parser.add_argument('--port', type=int, default=12345)
+    args = parser.parse_args()
+
+    host = (args.host, args.port)
+    print('Server running at http://%s:%s' % host)
+    server = HTTPServer(host, Request)
+    server.serve_forever()

run_qwen2.5_7B_axcl_context_tp.sh

@@ -0,0 +1,12 @@
+./main_tp_x86 \
+--template_filename_axmodel "qwen2.5_7b_tp/qwen2_p128_l%d_together.tar" \
+--axmodel_num 28 \
+--tokenizer_type 2 \
+--url_tokenizer_model "http://127.0.0.1:12345" \
+--filename_post_axmodel "qwen2.5_7b_tp/qwen2_post.tar" \
+--filename_tokens_embed "qwen2.5_7b_tp/model.embed_tokens.weight.bfloat16.bin" \
+--tokens_embed_num 152064 \
+--tokens_embed_size 3584 \
+--use_mmap_load_embed 1 \
+--live_print 1 \
+--devices 0,1,2,3