Call all LLM APIs using the OpenAI format. Use Bedrock, Azure, OpenAI, Cohere, Anthropic, Ollama, Sagemaker, HuggingFace, Replicate (100+ LLMs)
10.16k
stars
1.13k
forks
source link
[Bug]: Cleanup error message tpm/rpm limit hit -> `max_parallel_requests limit reached` #4314
Open
krrishdholakia opened 1 week ago
What happened?
I'm seeing a "max_parallel_requests limit reached" error when I hit the key's token limit
Which I think would confuse users.
Relevant log output
user request
Twitter / LinkedIn details
No response