From a834acf90a0f92960324c1cb08929975336a2342 Mon Sep 17 00:00:00 2001
From: mtrujillo <42344046+trujillm@users.noreply.github.com>
Date: Wed, 15 Oct 2025 17:27:30 -0400
Subject: [PATCH 1/4] add logic to check login for HF

---
 .../vllm-inference-service/templates/inference-service.yaml    | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/charts/all/vllm-inference-service/templates/inference-service.yaml b/charts/all/vllm-inference-service/templates/inference-service.yaml
index 8d63b817..358be306 100644
--- a/charts/all/vllm-inference-service/templates/inference-service.yaml
+++ b/charts/all/vllm-inference-service/templates/inference-service.yaml
@@ -37,7 +37,8 @@ spec:
             import os
             token = os.environ.get("HF_TOKEN")
             model = os.environ.get("MODEL_ID")
-            login(token=token)
+            if token:
+                login(token=token)
             snapshot_download(
                 repo_id=model,
                 local_dir="/cache/models"

From 0859d8c9db2109bfff61985d2eb567226f17deee Mon Sep 17 00:00:00 2001
From: mtrujillo <42344046+trujillm@users.noreply.github.com>
Date: Sun, 19 Oct 2025 19:42:21 -0400
Subject: [PATCH 2/4] update check for hf_token

---
 .../vllm-inference-service/templates/inference-service.yaml  | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/charts/all/vllm-inference-service/templates/inference-service.yaml b/charts/all/vllm-inference-service/templates/inference-service.yaml
index 358be306..2aa29318 100644
--- a/charts/all/vllm-inference-service/templates/inference-service.yaml
+++ b/charts/all/vllm-inference-service/templates/inference-service.yaml
@@ -35,10 +35,13 @@ spec:
             python - <<'PY'
             from huggingface_hub import snapshot_download, login
             import os
-            token = os.environ.get("HF_TOKEN")
+            token = os.environ.get("HF_TOKEN", "").strip()
             model = os.environ.get("MODEL_ID")
             if token:
+                print("HF_TOKEN found, logging in to Hugging Face...")
                 login(token=token)
+            else:
+                print("No HF_TOKEN found, downloading model without authentication...")
             snapshot_download(
                 repo_id=model,
                 local_dir="/cache/models"

From f59f8490c0bb20b440add98a89abfec40888507f Mon Sep 17 00:00:00 2001
From: mtrujillo <42344046+trujillm@users.noreply.github.com>
Date: Sun, 19 Oct 2025 19:59:48 -0400
Subject: [PATCH 3/4] add optional for secret

---
 .../all/vllm-inference-service/templates/inference-service.yaml  | 1 +
 1 file changed, 1 insertion(+)

diff --git a/charts/all/vllm-inference-service/templates/inference-service.yaml b/charts/all/vllm-inference-service/templates/inference-service.yaml
index 2aa29318..f537d553 100644
--- a/charts/all/vllm-inference-service/templates/inference-service.yaml
+++ b/charts/all/vllm-inference-service/templates/inference-service.yaml
@@ -55,6 +55,7 @@ spec:
               secretKeyRef:
                 name: huggingface-secret
                 key: hftoken
+                optional: true
           - name: MODEL_ID
             value: {{ .Values.global.model.vllm | quote }}
         volumeMounts:

From 2575da4f1517cbad53375c5b257394cc4e7385fb Mon Sep 17 00:00:00 2001
From: mtrujillo <42344046+trujillm@users.noreply.github.com>
Date: Mon, 20 Oct 2025 08:29:55 -0400
Subject: [PATCH 4/4] updating login logic check

---
 .../templates/inference-service.yaml                 | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/charts/all/vllm-inference-service/templates/inference-service.yaml b/charts/all/vllm-inference-service/templates/inference-service.yaml
index f537d553..d7da50ee 100644
--- a/charts/all/vllm-inference-service/templates/inference-service.yaml
+++ b/charts/all/vllm-inference-service/templates/inference-service.yaml
@@ -35,13 +35,15 @@ spec:
             python - <<'PY'
             from huggingface_hub import snapshot_download, login
             import os
-            token = os.environ.get("HF_TOKEN", "").strip()
+            raw_token = os.environ.get("HF_TOKEN", "")
+            token = raw_token.strip()
             model = os.environ.get("MODEL_ID")
-            if token:
-                print("HF_TOKEN found, logging in to Hugging Face...")
-                login(token=token)
+            if not token or not token.startswith("hf_"):
+                print("[HF] HF_TOKEN empty or invalid format; skipping login")
+                os.environ.pop("HF_TOKEN", None)
             else:
-                print("No HF_TOKEN found, downloading model without authentication...")
+                print("[HF] HF_TOKEN present; attempting login")
+                login(token=token)
             snapshot_download(
                 repo_id=model,
                 local_dir="/cache/models"