Closed NikitaSemenovAiforia closed 10 months ago
I got an error: ValueError: Model meta-llama/Llama-2-7b-chat-hf cannot automatically infer max_batch_total_tokens. Make sure to set engine_config.scheduler.policy.max_batch_total_tokens in the model configuration yaml.
this should be fixed now, please retry
I got an error: ValueError: Model meta-llama/Llama-2-7b-chat-hf cannot automatically infer max_batch_total_tokens. Make sure to set engine_config.scheduler.policy.max_batch_total_tokens in the model configuration yaml.