Hi
I am trying to install NIM models with enterprise API KEY. Once the LLM pod is running i see errors with certification and “hostname mismatch”.
Have not seen this error before. Not sure if any firewall/Proxy blocking the model to download necessary files or not.
Below is the error and this i have seen for other LLM NIM model as well.
Starting with this
INFO 11-26 18:00:58 [init.py:248] Automatically detected platform cuda.
:1297: FutureWarning: The cuda.cuda module is deprecated and will be removed in a future release, please switch to use the cuda.bindings.driver module instead.
INFO 2025-11-26 18:01:03.43 init.py:30] Available plugins for group vllm.general_plugins:
INFO 2025-11-26 18:01:03.43 init.py:32] name=lora_filesystem_resolver, value=vllm.plugins.lora_resolvers.filesystem_resolver:register_filesystem_resolver
INFO 2025-11-26 18:01:03.43 init.py:34] all available plugins for group vllm.general_plugins will be loaded.
INFO 2025-11-26 18:01:03.43 init.py:36] set environment variable VLLM_PLUGINS to control which plugins to load.
INFO 2025-11-26 18:01:03.44 init.py:44] plugin lora_filesystem_resolver loaded.
INFO 2025-11-26 18:01:03.498 args.py:178] Added MacheteLinearKernel to VLLM_DISABLED_KERNELS (applies to vLLM quantized models only)
WARNING 2025-11-26 18:01:03.944 utils.py:33] Error in fetching config.json for profile with id 09fec372bdcfaee0662140bc5ed522900bb0b0da7cc37ceba6209731dc55a689 and tags feat_lora:false|gpu:a10g|gpu_device:2237:10de|llm_engine:tensorrt_llm|nim_workspace_hash_v1:c0232176c2e5374758e3d88ea13e70aa0edca0862c923428f54b85da208960a9|number_of_gpus:4|pp:1|precision:bf16|profile:latency|tp:4. Original download error: ConnectionError: Check your ability to access the remote source and any network/dns/firewall/proxy settings. Details: reqwest::Error { kind: Request, url: “https://api.ngc.nvidia.com/v2/org/nim/team/meta/models/llama-3.1-8b-instruct/8c22764a7e3675c50d4c7c9a4edb474456022b16/files”, source: hyper_util::client::legacy::Error(Connect, Ssl(Error { code: ErrorCode(5), cause: Some(Ssl(ErrorStack([Error { code: 2147483650, library: “system library”, function: “file_open”, file: “providers/implementations/storemgmt/file_store.c”, line: 263, data: “calling stat(/etc/pki/tls/certs)” }, Error { code: 167772294, library: “SSL routines”, function: “tls_post_process_server_certificate”, reason: “certificate verify failed”, file: “ssl/statem/statem_clnt.c”, line: 2102 }]))) }, X509VerifyResult { code: 62, error: “hostname mismatch” })) }
WARNING 2025-11-26 18:01:03.944 profile_utils.py:881] Profile 0ba475f31abaf7997a551a5e0b0d77f3d0bcec73c03f815bf80e6cf5236f29d2 supports LoRA, but LoRA is disabled. Skipping profile.
WARNING 2025-11-26 18:01:04.3 utils.py:33] Error in fetching config.json for profile with id 0c87e2871cd7a6ea205a137109c3afde0134ba22c6fe8e978a752287cf561643 and tags feat_lora:false|gpu:h100_nvl|gpu_device:2321:10de|llm_engine:tensorrt_llm|nim_workspace_hash_v1:cb6ac7eedef673edc08e85f4f3e7525c31f499e5c5f376cbffc05cb8eefe197a|number_of_gpus:4|pp:1|precision:fp8|profile:latency|tp:2. Original download error: ConnectionError: Check your ability to access the remote source and any network/dns/firewall/proxy settings. Details: reqwest::Error { kind: Request, url: “https://api.ngc.nvidia.com/v2/org/nim/team/meta/models/llama-3.1-8b-instruct/8c22764a7e3675c50d4c7c9a4edb474456022b16/files”, source: hyper_util::client::legacy::Error(Connect, Ssl(Error { code: ErrorCode(5), cause: Some(Ssl(ErrorStack([Error { code: 2147483650, library: “system library”, function: “file_open”, file: “providers/implementations/storemgmt/file_store.c”, line: 263, data: “calling stat(/etc/pki/tls/certs)” }, Error { code: 167772294, library: “SSL routines”, function: “tls_post_process_server_certificate”, reason: “certificate verify failed”, file: “ssl/statem/statem_clnt.c”, line: 2102 }]))) }, X509VerifyResult { code: 62, error: “hostname mismatch” })) }
And then last error message:
Exception: ConnectionError: Check your ability to access the remote source and any network/dns/firewall/proxy settings. Details: reqwest::Error { kind: Request, url: “https://api.ngc.nvidia.com/v2/org/nim/team/meta/models/llama-3.1-8b-instruct/8c22764a7e3675c50d4c7c9a4edb474456022b16/files”, source: hyper_util::client::legacy::Error(Connect, Ssl(Error { code: ErrorCode(5), cause: Some(Ssl(ErrorStack([Error { code: 2147483650, library: “system library”, function: “file_open”, file: “providers/implementations/storemgmt/file_store.c”, line: 263, data: “calling stat(/etc/pki/tls/certs)” }, Error { code: 167772294, library: “SSL routines”, function: “tls_post_process_server_certificate”, reason: “certificate verify failed”, file: “ssl/statem/statem_clnt.c”, line: 2102 }]))) }, X509VerifyResult { code: 62, error: “hostname mismatch” })) }
Any idea?