Gary Wang
I also suffer the same issue with qat1.7.l.4.6.0-00025 when enable-kapi added, ... [ 1207.582776] qat_api: Unknown symbol adf_module_load (err -2) [ 1207.582816] qat_api: Unknown symbol icpSetProcessName (err -2) [ 1207.582851]...
Got it! I will remove ARC770 to test my iGPU again in MTL. BTW I also test the same SW environment in my TGL platform (Corei7-1185G7) and the iGPU indeed...
@qiuxin2012 . I confirmed MTL-H iGPU works well without ARC770 in platform. ``` [opencl:acc:0] Intel(R) FPGA Emulation Platform for OpenCL(TM), Intel(R) FPGA Emulation Device OpenCL 1.2 [2024.17.3.0.08_160000] [opencl:cpu:1] Intel(R) OpenCL,...
I saw docker image have been recovered. :) and issue resolved. `https://hub.docker.com/layers/intelanalytics/ipex-llm-inference-cpp-xpu/latest/images/sha256-2b854e8636795e512b17fe6858c34c08485e30a71350622e80a0d964cf7624e5`
@Oscilloscope98 , I skipped warmup phase via directly running "python startup.py -a" with following environment settings but still got failed. ``` ... export SYCL_CACHE_PERSISTENT=1 export BIGDL_LLM_XMX_DISABLED=1 export BIGDL_IMPORT_IPEX=0 export no_proxy=localhost,127.0.0.1...
Me too. it is suffering build failed via [ipex-llm docker](https://github.com/intel/ipex-llm/blob/main/docs/mddocs/DockerGuides/docker_cpp_xpu_quickstart.md) and found image has been removed. ``` intel@mydevice:~$ sudo docker login USING WEB-BASED LOGIN i Info → To sign in...
Add more info into issue description and thank you for help!
The same test on my ARL 255H ``` =========First token cost 2.7320 s and 11.611328125 GB========= =========Rest tokens cost average 0.0967 s (475 tokens in all) and 11.669921875 GB========= Inference...
Hello all, I have the same ARL 255H+DDR5-5600 (GPU runtime: **25.22.33944.8** via Linux kernel 6.16.0-rc6 [Linux]) environment then test them quickly via 3 version of IPEX -LLM (for llama.cpp). The...