ipex-llm 2.2.0b20250219__py3-none-manylinux2010_x86_64.whl → 2.2.0b20250221__py3-none-manylinux2010_x86_64.whl

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (10) hide show
  1. ipex_llm/vllm/xpu/entrypoints/openai/api_server.py +7 -3
  2. ipex_llm/vllm/xpu/model_convert.py +6 -4
  3. {ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/METADATA +19 -19
  4. {ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/RECORD +10 -10
  5. {ipex_llm-2.2.0b20250219.data → ipex_llm-2.2.0b20250221.data}/scripts/ipex-llm-init +0 -0
  6. {ipex_llm-2.2.0b20250219.data → ipex_llm-2.2.0b20250221.data}/scripts/llm-chat +0 -0
  7. {ipex_llm-2.2.0b20250219.data → ipex_llm-2.2.0b20250221.data}/scripts/llm-cli +0 -0
  8. {ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/WHEEL +0 -0
  9. {ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/entry_points.txt +0 -0
  10. {ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/top_level.txt +0 -0
ipex_llm/vllm/xpu/entrypoints/openai/api_server.py CHANGED
@@ -278,6 +278,10 @@ def base(request: Request) -> OpenAIServing:
278
278
  return tokenization(request)
279
279
 
280
280
 
281
+ def models(request: Request) -> OpenAIServingModels:
282
+ return request.app.state.openai_serving_models
283
+
284
+
281
285
  def chat(request: Request) -> Optional[OpenAIServingChat]:
282
286
  return request.app.state.openai_serving_chat
283
287
 
@@ -345,10 +349,10 @@ async def detokenize(request: DetokenizeRequest, raw_request: Request):
345
349
 
346
350
  @router.get("/v1/models")
347
351
  async def show_available_models(raw_request: Request):
348
- handler = base(raw_request)
352
+ handler = models(raw_request)
349
353
 
350
- models = await handler.show_available_models()
351
- return JSONResponse(content=models.model_dump())
354
+ models_ = await handler.show_available_models()
355
+ return JSONResponse(content=models_.model_dump())
352
356
 
353
357
 
354
358
  @router.get("/version")
ipex_llm/vllm/xpu/model_convert.py CHANGED
@@ -93,10 +93,12 @@ def get_load_function(low_bit):
93
93
  vllm_config=new_vllm_config
94
94
  )
95
95
  if self.vllm_config.model_config.low_bit_model_path is None:
96
- if "qwen" in self.vllm_config.model_config.model.lower() or \
97
- "baichuan" in self.vllm_config.model_config.model.lower() or \
98
- "codegeex4-all" in self.vllm_config.model_config.model.lower() or \
99
- "chatglm" in self.vllm_config.model_config.model.lower():
96
+ if ("qwen" in self.vllm_config.model_config.model.lower() or
97
+ "baichuan" in self.vllm_config.model_config.model.lower() or
98
+ "codegeex4-all" in self.vllm_config.model_config.model.lower() or
99
+ "chatglm" in self.vllm_config.model_config.model.lower()) and \
100
+ "gptq" not in self.model_config.model.lower() and \
101
+ "awq" not in self.model_config.model.lower():
100
102
  self.model.apply(padding_mlp)
101
103
  from ipex_llm import optimize_model
102
104
  not_convert_last_mlp = os.getenv("IPEX_LLM_NOT_CONVERT_LAST_MLP", None)
{ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/METADATA RENAMED
@@ -1,6 +1,6 @@
1
1
  Metadata-Version: 2.1
2
2
  Name: ipex-llm
3
- Version: 2.2.0b20250219
3
+ Version: 2.2.0b20250221
4
4
  Summary: Large Language Model Develop Toolkit
5
5
  Home-page: https://github.com/intel-analytics/ipex-llm
6
6
  Author: BigDL Authors
@@ -27,7 +27,7 @@ Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine
27
27
  Requires-Dist: torch ==2.1.2+cpu ; (platform_system == "Linux") and extra == 'all'
28
28
  Requires-Dist: torch ==2.1.2 ; (platform_system == "Windows") and extra == 'all'
29
29
  Provides-Extra: cpp
30
- Requires-Dist: bigdl-core-cpp ==2.6.0b20250219 ; extra == 'cpp'
30
+ Requires-Dist: bigdl-core-cpp ==2.6.0b20250221 ; extra == 'cpp'
31
31
  Requires-Dist: setuptools ; extra == 'cpp'
32
32
  Requires-Dist: onednn-devel ==2025.0.1 ; (platform_system == "Windows") and extra == 'cpp'
33
33
  Requires-Dist: onednn ==2025.0.1 ; (platform_system == "Windows") and extra == 'cpp'
@@ -60,7 +60,7 @@ Requires-Dist: transformers ==4.40.0 ; extra == 'npu'
60
60
  Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine == "AMD64") and extra == 'npu'
61
61
  Requires-Dist: torch ==2.1.2+cpu ; (platform_system == "Linux") and extra == 'npu'
62
62
  Requires-Dist: torch ==2.1.2 ; (platform_system == "Windows") and extra == 'npu'
63
- Requires-Dist: bigdl-core-npu ==2.6.0b20250219 ; (platform_system == "Windows") and extra == 'npu'
63
+ Requires-Dist: bigdl-core-npu ==2.6.0b20250221 ; (platform_system == "Windows") and extra == 'npu'
64
64
  Provides-Extra: serving
65
65
  Requires-Dist: py-cpuinfo ; extra == 'serving'
66
66
  Requires-Dist: fschat[model_worker,webui] ==0.2.36 ; extra == 'serving'
@@ -80,9 +80,9 @@ Requires-Dist: setuptools <70.0.0 ; extra == 'xpu'
80
80
  Requires-Dist: torch ==2.1.0a0 ; extra == 'xpu'
81
81
  Requires-Dist: torchvision ==0.16.0a0 ; extra == 'xpu'
82
82
  Requires-Dist: intel-extension-for-pytorch ==2.1.10+xpu ; extra == 'xpu'
83
- Requires-Dist: bigdl-core-xe-21 ==2.6.0b20250219 ; extra == 'xpu'
84
- Requires-Dist: bigdl-core-xe-batch-21 ==2.6.0b20250219 ; extra == 'xpu'
85
- Requires-Dist: bigdl-core-xe-addons-21 ==2.6.0b20250219 ; extra == 'xpu'
83
+ Requires-Dist: bigdl-core-xe-21 ==2.6.0b20250221 ; extra == 'xpu'
84
+ Requires-Dist: bigdl-core-xe-batch-21 ==2.6.0b20250221 ; extra == 'xpu'
85
+ Requires-Dist: bigdl-core-xe-addons-21 ==2.6.0b20250221 ; extra == 'xpu'
86
86
  Provides-Extra: xpu-2-1
87
87
  Requires-Dist: py-cpuinfo ; extra == 'xpu-2-1'
88
88
  Requires-Dist: protobuf ; extra == 'xpu-2-1'
@@ -97,9 +97,9 @@ Requires-Dist: setuptools <70.0.0 ; extra == 'xpu-2-1'
97
97
  Requires-Dist: torch ==2.1.0a0 ; extra == 'xpu-2-1'
98
98
  Requires-Dist: torchvision ==0.16.0a0 ; extra == 'xpu-2-1'
99
99
  Requires-Dist: intel-extension-for-pytorch ==2.1.10+xpu ; extra == 'xpu-2-1'
100
- Requires-Dist: bigdl-core-xe-21 ==2.6.0b20250219 ; extra == 'xpu-2-1'
101
- Requires-Dist: bigdl-core-xe-batch-21 ==2.6.0b20250219 ; extra == 'xpu-2-1'
102
- Requires-Dist: bigdl-core-xe-addons-21 ==2.6.0b20250219 ; extra == 'xpu-2-1'
100
+ Requires-Dist: bigdl-core-xe-21 ==2.6.0b20250221 ; extra == 'xpu-2-1'
101
+ Requires-Dist: bigdl-core-xe-batch-21 ==2.6.0b20250221 ; extra == 'xpu-2-1'
102
+ Requires-Dist: bigdl-core-xe-addons-21 ==2.6.0b20250221 ; extra == 'xpu-2-1'
103
103
  Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine == "AMD64") and extra == 'xpu-2-1'
104
104
  Requires-Dist: dpcpp-cpp-rt ==2024.0.2 ; (platform_system == "Windows") and extra == 'xpu-2-1'
105
105
  Requires-Dist: mkl-dpcpp ==2024.0.0 ; (platform_system == "Windows") and extra == 'xpu-2-1'
@@ -117,7 +117,7 @@ Requires-Dist: setuptools ; extra == 'xpu-2-6'
117
117
  Requires-Dist: torch ==2.6.0+xpu ; extra == 'xpu-2-6'
118
118
  Requires-Dist: torchvision ==0.21.0+xpu ; extra == 'xpu-2-6'
119
119
  Requires-Dist: torchaudio ==2.6.0+xpu ; extra == 'xpu-2-6'
120
- Requires-Dist: bigdl-core-xe-all ==2.6.0b20250219 ; extra == 'xpu-2-6'
120
+ Requires-Dist: bigdl-core-xe-all ==2.6.0b20250221 ; extra == 'xpu-2-6'
121
121
  Requires-Dist: onednn-devel ==2025.0.1 ; extra == 'xpu-2-6'
122
122
  Requires-Dist: onednn ==2025.0.1 ; extra == 'xpu-2-6'
123
123
  Requires-Dist: dpcpp-cpp-rt ==2025.0.2 ; extra == 'xpu-2-6'
@@ -133,9 +133,9 @@ Requires-Dist: tokenizers ==0.15.2 ; extra == 'xpu-arc'
133
133
  Requires-Dist: accelerate ==0.23.0 ; extra == 'xpu-arc'
134
134
  Requires-Dist: tabulate ; extra == 'xpu-arc'
135
135
  Requires-Dist: setuptools ; extra == 'xpu-arc'
136
- Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250219 ; extra == 'xpu-arc'
137
- Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250219 ; extra == 'xpu-arc'
138
- Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250219 ; extra == 'xpu-arc'
136
+ Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250221 ; extra == 'xpu-arc'
137
+ Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250221 ; extra == 'xpu-arc'
138
+ Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250221 ; extra == 'xpu-arc'
139
139
  Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine == "AMD64") and extra == 'xpu-arc'
140
140
  Requires-Dist: torch ==2.3.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-arc'
141
141
  Requires-Dist: torchvision ==0.18.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-arc'
@@ -156,9 +156,9 @@ Requires-Dist: tokenizers ==0.15.2 ; extra == 'xpu-arl'
156
156
  Requires-Dist: accelerate ==0.23.0 ; extra == 'xpu-arl'
157
157
  Requires-Dist: tabulate ; extra == 'xpu-arl'
158
158
  Requires-Dist: setuptools ; extra == 'xpu-arl'
159
- Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250219 ; extra == 'xpu-arl'
160
- Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250219 ; extra == 'xpu-arl'
161
- Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250219 ; extra == 'xpu-arl'
159
+ Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250221 ; extra == 'xpu-arl'
160
+ Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250221 ; extra == 'xpu-arl'
161
+ Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250221 ; extra == 'xpu-arl'
162
162
  Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine == "AMD64") and extra == 'xpu-arl'
163
163
  Requires-Dist: torch ==2.3.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-arl'
164
164
  Requires-Dist: torchvision ==0.18.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-arl'
@@ -179,9 +179,9 @@ Requires-Dist: tokenizers ==0.15.2 ; extra == 'xpu-lnl'
179
179
  Requires-Dist: accelerate ==0.23.0 ; extra == 'xpu-lnl'
180
180
  Requires-Dist: tabulate ; extra == 'xpu-lnl'
181
181
  Requires-Dist: setuptools ; extra == 'xpu-lnl'
182
- Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250219 ; extra == 'xpu-lnl'
183
- Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250219 ; extra == 'xpu-lnl'
184
- Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250219 ; extra == 'xpu-lnl'
182
+ Requires-Dist: bigdl-core-xe-23 ==2.6.0b20250221 ; extra == 'xpu-lnl'
183
+ Requires-Dist: bigdl-core-xe-batch-23 ==2.6.0b20250221 ; extra == 'xpu-lnl'
184
+ Requires-Dist: bigdl-core-xe-addons-23 ==2.6.0b20250221 ; extra == 'xpu-lnl'
185
185
  Requires-Dist: intel-openmp ; (platform_machine == "x86_64" or platform_machine == "AMD64") and extra == 'xpu-lnl'
186
186
  Requires-Dist: torch ==2.3.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-lnl'
187
187
  Requires-Dist: torchvision ==0.18.1+cxx11.abi ; (platform_system == "Linux") and extra == 'xpu-lnl'
{ipex_llm-2.2.0b20250219.dist-info → ipex_llm-2.2.0b20250221.dist-info}/RECORD RENAMED
@@ -255,16 +255,16 @@ ipex_llm/vllm/cpu/entrypoints/openai/cli_args.py,sha256=hB398yYtKauASRzevctScdbF
255
255
  ipex_llm/vllm/xpu/__init__.py,sha256=zBSG6nzrVF5QnpR6_f7kPhBFeowTE9gaZ7D5m98E7_w,585
256
256
  ipex_llm/vllm/xpu/ipex_llm_v1_wrapper.py,sha256=pd939vFomKIg9Qn2NO4u0OF6hPgvQpqcfJSxqBzcqhA,825
257
257
  ipex_llm/vllm/xpu/ipex_llm_wrapper.py,sha256=_CbhvBuf_KPnmLfngYKtJl5gPAHVsG2mWth3wSeaH3M,892
258
- ipex_llm/vllm/xpu/model_convert.py,sha256=4s7OxAUhxC2QpIf_yznrd-AL_Eu-ozaEr3tPTyCgS-c,8882
258
+ ipex_llm/vllm/xpu/model_convert.py,sha256=pSiJlmoktCPQIGzBuDBMWiCyASqgSAQpEbqWkYe00JQ,9029
259
259
  ipex_llm/vllm/xpu/engine/__init__.py,sha256=pY_CpyuZd72fr6s32ejeKHKFW0K4vUU2rzZjWqm5YiA,783
260
260
  ipex_llm/vllm/xpu/engine/engine.py,sha256=NvCMbp0X8NVrOqbwm4FTvXOptTRLzu9jQsy37ZHnTk8,9493
261
- ipex_llm/vllm/xpu/entrypoints/openai/api_server.py,sha256=OScQFmAdrd-PyEyQ2Mr8fJrk_lC6MHqPraphVk-NDzw,33140
261
+ ipex_llm/vllm/xpu/entrypoints/openai/api_server.py,sha256=D577nxWlyoWaHXNXIEvS3ViKSSWL3XZq8D8t6izD7x4,33250
262
262
  ipex_llm/vllm/xpu/entrypoints/openai/cli_args.py,sha256=hB398yYtKauASRzevctScdbFIjiiSGMAe1bwEuIHrhY,10893
263
- ipex_llm-2.2.0b20250219.data/scripts/ipex-llm-init,sha256=fLQsT2dRL6H5bThb4GuIWotAuqoLsIxFwA-0c2qmaO8,6672
264
- ipex_llm-2.2.0b20250219.data/scripts/llm-chat,sha256=TdUnUmNapzuoe1c8IzrdVOQwWEg8IqsMSBRlOD3daZM,2249
265
- ipex_llm-2.2.0b20250219.data/scripts/llm-cli,sha256=RXGPlLElHxcKzoUxljEMBIAXbzCDysXL-Nxw-xF-7LU,2457
266
- ipex_llm-2.2.0b20250219.dist-info/METADATA,sha256=hCcROHeDK5347fIyeDN0YbL7WQAA3Ql7Ue9LFxtu2Q0,12369
267
- ipex_llm-2.2.0b20250219.dist-info/WHEEL,sha256=PPJcBMAZibF_2GFE9NmOJGqiaSMPiNFbJd6QaJjdA6Y,109
268
- ipex_llm-2.2.0b20250219.dist-info/entry_points.txt,sha256=TiUyBB2MRmfF3ko-pyAEzqeBCRnyhu27bNOAsWPp3e8,61
269
- ipex_llm-2.2.0b20250219.dist-info/top_level.txt,sha256=CGCMHM-SyqUabU4h8RqJ2KTYckQUO3LvIWwmUQ6Qbzw,9
270
- ipex_llm-2.2.0b20250219.dist-info/RECORD,,
263
+ ipex_llm-2.2.0b20250221.data/scripts/ipex-llm-init,sha256=fLQsT2dRL6H5bThb4GuIWotAuqoLsIxFwA-0c2qmaO8,6672
264
+ ipex_llm-2.2.0b20250221.data/scripts/llm-chat,sha256=TdUnUmNapzuoe1c8IzrdVOQwWEg8IqsMSBRlOD3daZM,2249
265
+ ipex_llm-2.2.0b20250221.data/scripts/llm-cli,sha256=RXGPlLElHxcKzoUxljEMBIAXbzCDysXL-Nxw-xF-7LU,2457
266
+ ipex_llm-2.2.0b20250221.dist-info/METADATA,sha256=O0dk_kgnXxjRV7TqB1H_XjXeBDZ5LPXDBLJABn3KvDg,12369
267
+ ipex_llm-2.2.0b20250221.dist-info/WHEEL,sha256=PPJcBMAZibF_2GFE9NmOJGqiaSMPiNFbJd6QaJjdA6Y,109
268
+ ipex_llm-2.2.0b20250221.dist-info/entry_points.txt,sha256=TiUyBB2MRmfF3ko-pyAEzqeBCRnyhu27bNOAsWPp3e8,61
269
+ ipex_llm-2.2.0b20250221.dist-info/top_level.txt,sha256=CGCMHM-SyqUabU4h8RqJ2KTYckQUO3LvIWwmUQ6Qbzw,9
270
+ ipex_llm-2.2.0b20250221.dist-info/RECORD,,