VertexAI provider is broken

[nathan-weinberg]

System Info

<frozen runpy>:128: RuntimeWarning: 'torch.utils.collect_env' found in sys.modules after import of package 'torch.utils', but prior to execution of 'torch.utils.collect_env'; this may result in unpredictable behaviour
Collecting environment information...
PyTorch version: 2.9.0+cpu
Is debug build: False
CUDA used to build PyTorch: None
ROCM used to build PyTorch: N/A

OS: Fedora Linux 41 (Workstation Edition) (x86_64)
GCC version: Could not collect
Clang version: Could not collect
CMake version: Could not collect
Libc version: glibc-2.40

Python version: 3.12.12 (main, Oct 10 2025, 00:00:00) [GCC 14.3.1 20250808 (Red Hat 14.3.1-3)] (64-bit runtime)
Python platform: Linux-6.16.7-100.fc41.x86_64-x86_64-with-glibc2.40
Is CUDA available: False
CUDA runtime version: No CUDA
CUDA_MODULE_LOADING set to: N/A
GPU models and configuration: No CUDA
Nvidia driver version: No CUDA
cuDNN version: No CUDA
Is XPU available: False
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                            x86_64
CPU op-mode(s):                          32-bit, 64-bit
Address sizes:                           52 bits physical, 57 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) w5-3423
CPU family:                              6
Model:                                   143
Thread(s) per core:                      2
Core(s) per socket:                      12
Socket(s):                               1
Stepping:                                8
CPU(s) scaling MHz:                      34%
CPU max MHz:                             4200.0000
CPU min MHz:                             800.0000
BogoMIPS:                                4224.00
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 art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq 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 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 intel_ppin cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect user_shstk avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req vnmi avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                          VT-x
L1d cache:                               576 KiB (12 instances)
L1i cache:                               384 KiB (12 instances)
L2 cache:                                24 MiB (12 instances)
L3 cache:                                30 MiB (1 instance)
NUMA node(s):                            1
NUMA node0 CPU(s):                       0-23
Vulnerability Gather data sampling:      Not affected
Vulnerability Ghostwrite:                Not affected
Vulnerability Indirect target selection: Not affected
Vulnerability Itlb multihit:             Not affected
Vulnerability L1tf:                      Not affected
Vulnerability Mds:                       Not affected
Vulnerability Meltdown:                  Not affected
Vulnerability Mmio stale data:           Not affected
Vulnerability Old microcode:             Vulnerable
Vulnerability Reg file data sampling:    Not affected
Vulnerability Retbleed:                  Not affected
Vulnerability Spec rstack overflow:      Not affected
Vulnerability Spec store bypass:         Mitigation; Speculative Store Bypass disabled via prctl
Vulnerability Spectre v1:                Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:                Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                     Not affected
Vulnerability Tsa:                       Not affected
Vulnerability Tsx async abort:           Not affected
Vulnerability Vmscape:                   Mitigation; IBPB before exit to userspace

Versions of relevant libraries:
[pip3] Could not collect
[conda] Could not collect

Information

• The official example scripts
• My own modified scripts

🐛 Describe the bug

#3547 introduced dynamic model listings for several providers including VertexAI which was previously using hardcoded values. The PR makes the assumption that each provider endpoints has an Open AI-compatible endpoint that implements model listing, which for Vertex AI would translate to https://${VERTEX_AI_LOCATION}-aiplatform.googleapis.com/v1/projects/${VERTEX_AI_PROJECT}/locations/${VERTEX_AI_LOCATION}/endpoints/openapi/models

However, this endpoint is not in fact implemented by Vertex AI

$ curl -X GET -H "Authorization: Bearer $(gcloud auth print-access-token)" "https://us-east5-aiplatform.googleapis.com/v1/projects/it-cloud-gcp-instructlab-dev/locations/us-east5/endpoints/openai/models"
<!DOCTYPE html>
<html lang=en>
  <meta charset=utf-8>
  <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">
  <title>Error 404 (Not Found)!!1</title>
  <style>
    *{margin:0;padding:0}html,code{font:15px/22px arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto 0;max-width:390px;min-height:180px;padding:30px 0 15px}* > body{background:url(//www.google.com/images/errors/robot.png) 100% 5px no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a img{border:0}@media screen and (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only screen and (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat 0% 0%/100% 100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) 0}}@media only screen and (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png) no-repeat;-webkit-background-size:100% 100%}}#logo{display:inline-block;height:54px;width:150px}
  </style>
  <a href=//www.google.com/><span id=logo aria-label=Google></span></a>
  <p><b>404.</b> <ins>That’s an error.</ins>
  <p>The requested URL <code>/v1/projects/it-cloud-gcp-instructlab-dev/locations/us-east5/endpoints/openai/models</code> was not found on this server.  <ins>That’s all we know.</ins>

If you run the Llama Stack starter distro with Vertex AI enabled, the provider cannot be used - see the error logs below

Error logs

ERROR    2025-10-30 16:17:15,953 llama_stack.providers.utils.inference.openai_mixin:428 providers::utils:                                                                                                                    16:17:15 [9/1731]
         VertexAIInferenceAdapter.list_provider_model_ids() failed with: <!DOCTYPE html>                                                                                                                                                      
         <html lang=en>                                                                                                                                                                                                                       
           <meta charset=utf-8>                                                                                                                                                                                                               
           <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">                                                                                                                                                
           <title>Error 404 (Not Found)!!1</title>                                                                                                                                                                                            
           <style>                                                                                                                                                                                                                            
             *{margin:0;padding:0}html,code{font:15px/22px                                                                                                                                                                                    
         arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto                                                                                                                                                    
         0;max-width:390px;min-height:180px;padding:30px 0 15px}* >                                                                                                                                                                           
         body{background:url(//www.google.com/images/errors/robot.png) 100% 5px                                          
         no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a        
         img{border:0}@media screen and                                                                                  
         (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.
         google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only  
         screen and                                                                                                      
         (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_15
         0x54dp.png) no-repeat 0% 0%/100%                                                                                
         100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png)        
         0}}@media only screen and                                                                                       
         (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelo
         go_color_150x54dp.png) no-repeat;-webkit-background-size:100%                                                   
         100%}}#logo{display:inline-block;height:54px;width:150px}                                                       
           </style>                                                                                                      
           <a href=//www.google.com/><span id=logo aria-label=Google></span></a>                                         
           <p><b>404.</b> <ins>That’s an error.</ins>                                                                    
           <p>The requested URL                                                                                          
         <code>/v1/projects/it-cloud-gcp-instructlab-dev/locations/us-east5/endpoints/openapi/models</code> was not      
         found on this server.  <ins>That’s all we know.</ins>
WARNING  2025-10-30 16:17:15,957 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed    
         for provider vertexai: <!DOCTYPE html>                                                                          
         <html lang=en>                                                                                                  
           <meta charset=utf-8>                                                                                          
           <meta name=viewport content="initial-scale=1, minimum-scale=1, width=device-width">                           
           <title>Error 404 (Not Found)!!1</title>                                                                       
           <style>                                                                                                       
             *{margin:0;padding:0}html,code{font:15px/22px                                                               
         arial,sans-serif}html{background:#fff;color:#222;padding:15px}body{margin:7% auto                               
         0;max-width:390px;min-height:180px;padding:30px 0 15px}* >                                                      
         body{background:url(//www.google.com/images/errors/robot.png) 100% 5px                                          
         no-repeat;padding-right:205px}p{margin:11px 0 22px;overflow:hidden}ins{color:#777;text-decoration:none}a        
         img{border:0}@media screen and                                                                                  
         (max-width:772px){body{background:none;margin-top:0;max-width:none;padding-right:0}}#logo{background:url(//www.
         google.com/images/branding/googlelogo/1x/googlelogo_color_150x54dp.png) no-repeat;margin-left:-5px}@media only  
         screen and                                                                                                      
         (min-resolution:192dpi){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_15
         0x54dp.png) no-repeat 0% 0%/100%                                                                                
         100%;-moz-border-image:url(//www.google.com/images/branding/googlelogo/2x/googlelogo_color_150x54dp.png)        
         0}}@media only screen and                                                                                       
         (-webkit-min-device-pixel-ratio:2){#logo{background:url(//www.google.com/images/branding/googlelogo/2x/googlelo
         go_color_150x54dp.png) no-repeat;-webkit-background-size:100%                                                   
         100%}}#logo{display:inline-block;height:54px;width:150px}                                                       
           </style>                                                                                                      
           <a href=//www.google.com/><span id=logo aria-label=Google></span></a>                                         
           <p><b>404.</b> <ins>That’s an error.</ins>                                                                    
           <p>The requested URL                                                                                          
         <code>/v1/projects/it-cloud-gcp-instructlab-dev/locations/us-east5/endpoints/openapi/models</code> was not      
         found on this server.  <ins>That’s all we know.</ins> 

Expected behavior

Error and warning logs should not appear, Vertex AI provider should be able to provide a model list as before

[nathan-weinberg]

cc @bbrowning @cdoern @Artemon-line

[nathan-weinberg]

@mattf I'm thinking of reverting Vertex back to the hardcoded model listing that was done before the PR change - lmk what you think and if you agree you can assign me and I'll take care of it

[ashwinb]

Is there an endpoint for vertex AI which does implement model listing? If so there is facility to override the list_models() function within the provider to implement this. That would be the right thing to do.

[nathan-weinberg]

Is there an endpoint for vertex AI which does implement model listing? If so there is facility to override the list_models() function within the provider to implement this. That would be the right thing to do.

So Ben and I were looking at this - there's an endpoint to show models that you have trained, but seemingly there's no endpoint that lists models available from the "model garden" (where you would expect to get the list of models such as gemini-2.5-pro etc.)

[bbrowning]

I concur with Nathan - we were unable to find any working endpoint to let us list models via an API. One caveat is that the credentials I was using were sufficient to inference with Vertex AI but I'm not any kind of administrator with those credentials, so there may be something hidden behind some admin-only API somewhere. I'm also no expert in Vertex AI's APIs, but did google around, ask a few AI systems, and poke with curl and clients manually without finding anything.

[nathan-weinberg]

I did confirm with the account I'm using that I'm able to make a chat completion request to gemini-2.5-flash

curl -X POST \
  -H "Authorization: Bearer $(gcloud auth print-access-token)" \
  -H "Content-Type: application/json" \
  "https://${VERTEX_AI_LOCATION}-aiplatform.googleapis.com/v1beta1/projects/${VERTEX_AI_PROJECT}/locations/${VERTEX_AI_LOCATION}/endpoints/openapi/chat/completions" \
  -d '{
        "model": "google/gemini-2.5-flash",
        "messages": [
          {
            "role": "system",
            "content": "You are a helpful assistant."
          },
          {
            "role": "user",
            "content": "Hello! Can you tell me a joke?"
          }
        ],
        "temperature": 1.0,
        "max_tokens": 256
      }'
{"choices":[{"finish_reason":"stop","index":0,"logprobs":null,"message":{"content":"Why did the scarecrow win an award?\n\nBecause he was outstanding in his field!","role":"assistant"}}],"created":1761934621,"id":"Hf0EacSvGLGN1tEP3quxSQ","model":"google/gemini-2.5-flash","object":"chat.completion","system_fingerprint":"","usage":{"completion_tokens":18,"completion_tokens_details":{"reasoning_tokens":41},"extra_properties":{"google":{"traffic_type":"ON_DEMAND"}},"prompt_tokens":15,"total_tokens":74}}

So the models are available, there just doesn't seem to be a way, OpenAI-native or otherwise, to list them.

[ashwinb]

OK then, let's go ahead and revert it to hard coded model listings.

[nathan-weinberg]

Will do, can you assign me the issue?