apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-12-24 13:28:13 +08:00
Code Issues Actions 2 Packages Projects Releases Wiki Activity

[V1 loader] Qwen25 VL support v1 loader and torch style safetensors load (#4388)

Browse Source 
* [BugFix] qwen2.5vl enable_thinking=true and image_patch_id bug fix

* [Docs]offine infer add apply_chat_template add_generation_prompt parameter

* [Model]qwen2.5VL support --use-cudagraph

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v2

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v3

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v4

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v5

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v6

* [Model]qwen2.5VL support --use-cudagraph buffer and qwenvl test v7

* qwen25vl v1 loader

* qwen25vl v1 loader v2

* qwen25vl v1 loader v3

* qwen25vl v1 loader fix tp2 weight PySafeSlice

* qwen25vl v1 loader no test

* qwen25vl v1 loader add unit test

* qwen25vl v1 loader add unit test v2

* qwen25vl v1 loader add torch unit test v3

* qwen25vl v1 loader add torch unit test v4

* qwen25vl v1 loader add torch unit test v5

* qwen25vl v1 loader add torch unit test v6
This commit is contained in:
CSWYF3634076
2025-10-27 10:54:15 +08:00
committed by GitHub
parent 5c6105f4a2
commit acd331780c
8 changed files with 697 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
fastdeploy/input/qwen_vl_processor/qwen_vl_processor.py
View File

@@ -239,7 +239,7 @@ class QwenVLProcessor(TextProcessor):
request[k] = v
else:
raise ValueError("Invalid input: chat_template_kwargs must be a dict")
request.setdefault("enable_thinking", True)
request.setdefault("enable_thinking", False)
outputs = self.processor.request2ids(request)
else:
@@ -249,11 +249,8 @@ class QwenVLProcessor(TextProcessor):
if request.get("completion_token_ids"):
self.append_completion_tokens(outputs, request["completion_token_ids"])
enable_thinking = False
if request.get("chat_template_kwargs"):
chat_template_kwargs = request.get("chat_template_kwargs")
enable_thinking = chat_template_kwargs.get("enable_thinking", False)
request["enable_thinking"] = enable_thinking
# qwen25_vl not support thinking
request["enable_thinking"] = False
outputs = self.pack_outputs(outputs)