Failed to run gemma 7B - Githubissues

LocalAI version:

root@node1:~/cxl# crictl images | grep local-ai
quay.io/go-skynet/local-ai                  latest                    eb2dbec811326       16.2GB

Environment, CPU architecture, OS, and Version:

kubernetes v1.24.7
os: ubuntu 22.04
uname -a : Linux node1 6.2.0-26-generic #26~22.04.1-Ubuntu SMP PREEMPT_DYNAMIC Thu Jul 13 16:27:29 UTC 2 x86_64 x86_64 x86_64 GNU/Linux

cpu arch:

root@node1:~/# lscpu
Architecture:            x86_64
CPU op-mode(s):        32-bit, 64-bit
Address sizes:         46 bits physical, 48 bits virtual
Byte Order:            Little Endian
CPU(s):                  24
On-line CPU(s) list:   0-23
Vendor ID:               GenuineIntel
Model name:            Intel(R) Xeon(R) CPU E5-2678 v3 @ 2.50GHz
CPU family:          6
Model:               63
Thread(s) per core:  2
Core(s) per socket:  12
Socket(s):           1
Stepping:            2
CPU max MHz:         3300.0000
CPU min MHz:         1200.0000
BogoMIPS:            4988.32
Flags:               fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_ts
                     c cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm cpuid_fault epb i
                     nvpcid_single pti intel_ppin ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc dtherm ida arat pln pts md_clear fl
                     ush_l1d
Virtualization features:
Virtualization:        VT-x
Caches (sum of all):
L1d:                   384 KiB (12 instances)
L1i:                   384 KiB (12 instances)
L2:                    3 MiB (12 instances)
L3:                    30 MiB (1 instance)
NUMA:
NUMA node(s):          1
NUMA node0 CPU(s):     0-23
Vulnerabilities:
Itlb multihit:         KVM: Mitigation: VMX disabled
L1tf:                  Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Mds:                   Mitigation; Clear CPU buffers; SMT vulnerable
Meltdown:              Mitigation; PTI
Mmio stale data:       Mitigation; Clear CPU buffers; SMT vulnerable
Retbleed:              Not affected
Spec store bypass:     Mitigation; Speculative Store Bypass disabled via prctl
Spectre v1:            Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Spectre v2:            Mitigation; Retpolines, IBPB conditional, IBRS_FW, STIBP conditional, RSB filling, PBRSB-eIBRS Not affected
Srbds:                 Not affected
Tsx async abort:       Not affected

Describe the bug

Download gemma 7b from huggingface

Install local-ai on kubernetes cluster, pod yaml as below:

apiVersion: v1
kind: Pod
metadata:
name: localai
spec:
containers:
- name: local-ai-container
  image: quay.io/go-skynet/local-ai:latest
  resources:
    requests:
      cpu: 4
      memory: 4Gi
    limits:
      cpu: 8
      memory: 8Gi
  ports:
    - containerPort: 8080
      hostPort: 8080
  args:
    - "--models-path"
    - "/models"
    - "--context-size"
    - "700"
    - "--threads"
    - "4"
  volumeMounts:
    - name: models-volume
      mountPath: /models
volumes:
- name: models-volume
  hostPath:
    path: /root/cxl/models
    type: Directory

Send the request:

root@node1:~# curl http://100.67.166.160:8080/v1/completions -H "Content-Type: application/json" -d '{ "model": "gemma-7b.gguf", "prompt": "Hi, how are you?", "temperature": 0.5 }'
{"error":{"code":500,"message":"rpc error: code = Unknown desc = unimplemented","type":""}}

Expected behavior

Get a code 200 HTTP response.

Logs

@@@@@
Skipping rebuild
@@@@@
If you are experiencing issues with the pre-compiled builds, try setting REBUILD=true
If you are still experiencing issues with the build, try setting CMAKE_ARGS and disable the instructions set as needed:
CMAKE_ARGS="-DLLAMA_F16C=OFF -DLLAMA_AVX512=OFF -DLLAMA_AVX2=OFF -DLLAMA_FMA=OFF"
see the documentation at: https://localai.io/basics/build/index.html
Note: See also https://github.com/go-skynet/LocalAI/issues/288
@@@@@
CPU info:
model name  : Intel(R) Xeon(R) CPU E5-2678 v3 @ 2.50GHz
flags       : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm cpuid_fault epb invpcid_single pti intel_ppin ssbd ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm xsaveopt cqm_llc cqm_occup_llc dtherm ida arat pln pts md_clear flush_l1d
CPU:    AVX    found OK
CPU:    AVX2   found OK
CPU: no AVX512 found
@@@@@
5:56PM DBG no galleries to load
5:56PM INF Starting LocalAI using 4 threads, with models path: /models
5:56PM INF LocalAI version: v2.9.0 (ff88c390bb51d9567572815a63c575eb2e3dd062)
5:56PM INF Preloading models from /models

 ┌───────────────────────────────────────────────────┐
 │                   Fiber v2.50.0                   │
 │               http://127.0.0.1:8080               │
 │       (bound on host 0.0.0.0 and port 8080)       │
 │                                                   │
 │ Handlers ........... 105  Processes ........... 1 │
 │ Prefork ....... Disabled  PID ................ 14 │
 └───────────────────────────────────────────────────┘

5:57PM INF Trying to load the model 'gemma-7b.gguf' with all the available backends: llama-cpp, llama-ggml, llama, gpt4all, bert-embeddings, rwkv, whisper, stablediffusion, tinydream, piper, /build/backend/python/sentencetransformers/run.sh, /build/backend/python/transformers-musicgen/run.sh, /build/backend/python/autogptq/run.sh, /build/backend/python/diffusers/run.sh, /build/backend/python/transformers/run.sh, /build/backend/python/exllama2/run.sh, /build/backend/python/exllama/run.sh, /build/backend/python/mamba/run.sh, /build/backend/python/petals/run.sh, /build/backend/python/vall-e-x/run.sh, /build/backend/python/sentencetransformers/run.sh, /build/backend/python/coqui/run.sh, /build/backend/python/vllm/run.sh, /build/backend/python/bark/run.sh
5:57PM INF [llama-cpp] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend llama-cpp
5:57PM INF [llama-cpp] Fails: could not load model: rpc error: code = Unavailable desc = error reading from server: EOF
5:57PM INF [llama-ggml] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend llama-ggml
5:57PM INF [llama-ggml] Fails: could not load model: rpc error: code = Unknown desc = failed loading model
5:57PM INF [llama] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend llama
5:57PM INF [llama] Fails: could not load model: rpc error: code = Unavailable desc = error reading from server: EOF
5:57PM INF [gpt4all] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend gpt4all
5:57PM INF [gpt4all] Fails: could not load model: rpc error: code = Unknown desc = failed loading model
5:57PM INF [bert-embeddings] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend bert-embeddings
5:57PM INF [bert-embeddings] Fails: could not load model: rpc error: code = Unknown desc = failed loading model
5:57PM INF [rwkv] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend rwkv
5:57PM INF [rwkv] Fails: could not load model: rpc error: code = Unavailable desc = error reading from server: EOF
5:57PM INF [whisper] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend whisper
5:57PM INF [whisper] Fails: could not load model: rpc error: code = Unknown desc = unable to load model
5:57PM INF [stablediffusion] Attempting to load
5:57PM INF Loading model 'gemma-7b.gguf' with backend stablediffusion
5:57PM INF [stablediffusion] Loads OK

Additional context

IDK how much memory/cpu resources is required, but if I don't set the pod cpu/memory limit local-ai will use up all the memory and make this machine hang up in first request.

mudler / LocalAI

Failed to run gemma 7B #1806