search

mudler / LocalAI

:robot: The free, Open Source alternative to OpenAI, Claude and others. Self-hosted and local-first. Drop-in replacement for OpenAI, running on consumer-grade hardware. No GPU required. Runs gguf, transformers, diffusers and many more models architectures. Features: Generate Text, Audio, Video, Images, Voice Cloning, Distributed inference
https://localai.io
MIT License
24.06k stars 1.85k forks source link

LocalAI Docker Container won't start on Windows 11 #3588

Open FMarazzi opened 1 month ago

FMarazzi commented 1 month ago

LocalAI version: localai/localai:latest-aio-cpu

Environment, CPU architecture, OS, and Version: Docker Desktop, Ryzen 7 7800X3D, Windows 11 Pro

Describe the bug Container fails and exits.

To Reproduce Installed Docker Desktop, followed by: docker run -p 8080:8080 --name local-ai -ti localai/localai:latest-aio-cpu in the powershell.

Expected behavior For it to start.

Logs 2024-09-17 10:08:51 ===> LocalAI All-in-One (AIO) container starting... 2024-09-17 10:08:51 NVIDIA GPU detected via WSL2 2024-09-17 10:08:51 /aio/entrypoint.sh: line 26: nvidia-smi: command not found 2024-09-17 10:08:51 NVIDIA GPU detected via WSL2, but nvidia-smi is not installed. GPU acceleration will not be available. 2024-09-17 10:08:51 GPU acceleration is not enabled or supported. Defaulting to CPU. 2024-09-17 10:08:51 ===> Starting LocalAI[cpu] with the following models: /aio/cpu/embeddings.yaml,/aio/cpu/rerank.yaml,/aio/cpu/text-to-speech.yaml,/aio/cpu/image-gen.yaml,/aio/cpu/text-to-text.yaml,/aio/cpu/speech-to-text.yaml,/aio/cpu/vision.yaml 2024-09-17 10:08:51 @@@@@ 2024-09-17 10:08:51 Skipping rebuild 2024-09-17 10:08:51 @@@@@ 2024-09-17 10:08:51 If you are experiencing issues with the pre-compiled builds, try setting REBUILD=true 2024-09-17 10:08:51 If you are still experiencing issues with the build, try setting CMAKE_ARGS and disable the instructions set as needed: 2024-09-17 10:08:51 CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" 2024-09-17 10:08:51 see the documentation at: https://localai.io/basics/build/index.html 2024-09-17 10:08:51 Note: See also https://github.com/go-skynet/LocalAI/issues/288 2024-09-17 10:08:51 @@@@@ 2024-09-17 10:08:51 CPU info: 2024-09-17 10:08:51 model name : AMD Ryzen 7 7800X3D 8-Core Processor 2024-09-17 10:08:51 flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr arat npt nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm 2024-09-17 10:08:51 CPU: AVX found OK 2024-09-17 10:08:51 CPU: AVX2 found OK 2024-09-17 10:08:51 CPU: AVX512 found OK 2024-09-17 10:08:51 @@@@@ 2024-09-17 10:08:51 /build/entrypoint.sh: line 50: /build/local-ai: cannot execute binary file: Exec format error 2024-09-17 10:08:51 /build/entrypoint.sh: line 50: /build/local-ai: Success 2024-09-17 11:44:13 ===> LocalAI All-in-One (AIO) container starting... 2024-09-17 11:44:13 NVIDIA GPU detected via WSL2 2024-09-17 11:44:13 /aio/entrypoint.sh: line 26: nvidia-smi: command not found 2024-09-17 11:44:13 NVIDIA GPU detected via WSL2, but nvidia-smi is not installed. GPU acceleration will not be available. 2024-09-17 11:44:13 GPU acceleration is not enabled or supported. Defaulting to CPU. 2024-09-17 11:44:13 ===> Starting LocalAI[cpu] with the following models: /aio/cpu/embeddings.yaml,/aio/cpu/rerank.yaml,/aio/cpu/text-to-speech.yaml,/aio/cpu/image-gen.yaml,/aio/cpu/text-to-text.yaml,/aio/cpu/speech-to-text.yaml,/aio/cpu/vision.yaml 2024-09-17 11:44:13 @@@@@ 2024-09-17 11:44:13 Skipping rebuild 2024-09-17 11:44:13 @@@@@ 2024-09-17 11:44:13 If you are experiencing issues with the pre-compiled builds, try setting REBUILD=true 2024-09-17 11:44:13 If you are still experiencing issues with the build, try setting CMAKE_ARGS and disable the instructions set as needed: 2024-09-17 11:44:13 CMAKE_ARGS="-DGGML_F16C=OFF -DGGML_AVX512=OFF -DGGML_AVX2=OFF -DGGML_FMA=OFF" 2024-09-17 11:44:13 see the documentation at: https://localai.io/basics/build/index.html 2024-09-17 11:44:13 Note: See also https://github.com/go-skynet/LocalAI/issues/288 2024-09-17 11:44:13 @@@@@ 2024-09-17 11:44:13 CPU info: 2024-09-17 11:44:13 model name : AMD Ryzen 7 7800X3D 8-Core Processor 2024-09-17 11:44:13 flags : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good nopl tsc_reliable nonstop_tsc cpuid extd_apicid pni pclmulqdq ssse3 fma cx16 sse4_1 sse4_2 movbe popcnt aes xsave avx f16c rdrand hypervisor lahf_lm cmp_legacy svm cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw topoext perfctr_core ssbd ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves avx512_bf16 clzero xsaveerptr arat npt nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload avx512vbmi umip avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq rdpid fsrm 2024-09-17 11:44:13 CPU: AVX found OK 2024-09-17 11:44:13 CPU: AVX2 found OK 2024-09-17 11:44:13 CPU: AVX512 found OK 2024-09-17 11:44:13 @@@@@ 2024-09-17 11:44:13 /build/entrypoint.sh: line 50: /build/local-ai: cannot execute binary file: Exec format error 2024-09-17 11:44:13 /build/entrypoint.sh: line 50: /build/local-ai: Success

teddybear082 commented 1 day ago

I have the same: ===> LocalAI All-in-One (AIO) container starting... 2024-10-19 09:56:23 api-1 | NVIDIA GPU detected via WSL2 2024-10-19 09:56:23 api-1 | /aio/entrypoint.sh: line 26: nvidia-smi: command not found 2024-10-19 09:56:23 api-1 | NVIDIA GPU detected via WSL2, but nvidia-smi is not installed. GPU acceleration will not be available. 2024-10-19 09:56:23 api-1 | GPU acceleration is not enabled or supported. Defaulting to CPU.

anyone found a fix?