Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 5 additions & 0 deletions .changeset/llm-stack-fix-config-updates.md
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
---
"llm-stack": patch
---

Made the digest header for the apisix config update variable so that config updates are accepted by apisix
2 changes: 1 addition & 1 deletion charts/llm-stack/bin/test-request-scaleway.sh
Original file line number Diff line number Diff line change
@@ -1,7 +1,7 @@
PORT=${PORT:-80}
HOST=${HOST:-llm-stack.localhost}

curl http://$HOST:$PORT/v1/chat/completions \
curl http://$HOST:$PORT/v1/chat/completions -v \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-client-v1-abcdef123456" \
-d '{
Expand Down
5 changes: 0 additions & 5 deletions charts/llm-stack/examples/scaleway.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -4,11 +4,6 @@ apisixInitialConfig:
provider: openai-compatible
# retrieve the project id from the scaleway project dashboard
baseURL: "https://api.scaleway.ai/<project_id>/v1/chat/completions" # ignored if vllm is enabled
models:
- name: qwen3.6-35b-a3b
provider: scaleway
- name: gemma-4-26b-a4b-it
provider: scaleway

apisix:
metrics:
Expand Down
Original file line number Diff line number Diff line change
Expand Up @@ -18,12 +18,13 @@ data:
import sys
import json
import os
from datetime import datetime

url = "http://{{ include "common.names.fullname" . }}-apisix-admin-headless:9180/apisix/admin/configs"
headers = {
"X-API-KEY": os.getenv("ADMIN_API_KEY", ""),
"Content-Type": "application/json",
"X-DIGEST": "initial-config"
"X-DIGEST": str(datetime.now())
}

# Wait for APISIX Admin API to be ready
Expand Down Expand Up @@ -62,7 +63,8 @@ data:
"ai-rate-limiting": {
"limit": {{ .Values.apisixInitialConfig.consumerUsageLimits.numTokens}},
"time_window": {{ .Values.apisixInitialConfig.consumerUsageLimits.timeWindowSeconds }},
"limit_strategy": {{ .Values.apisixInitialConfig.consumerUsageLimits.limitStrategy | quote }}
"limit_strategy": {{ .Values.apisixInitialConfig.consumerUsageLimits.limitStrategy | quote }},
"rejected_code": 429
},
}
} for consumer in consumer_data
Expand Down
10 changes: 9 additions & 1 deletion charts/llm-stack/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -11,8 +11,16 @@ apisixInitialConfig:
provider: scaleway
- name: gemma-4-26b-a4b-it
provider: scaleway
- name: glm-5.2
provider: scaleway
- name: deepseek-v4-flash-0731
provider: scaleway
- name: qwen3.5-397b-a17b
provider: scaleway
- name: mistral-medium-3.5-128b
provider: scaleway
consumerUsageLimits:
numTokens: 10000000
numTokens: 50000000
timeWindowSeconds: 86400 # 24h
limitStrategy: total_tokens
secrets:
Expand Down
Loading