[Bug]: ValueError: Out of range float values are not JSON compliant
when requesting logprobs from awq model
#328
Labels
bug
Something isn't working
Your current environment
馃悰 Describe the bug
launch aphrodite with
python -m aphrodite.endpoints.openai.api_server --host 127.0.0.1 --port 5000 --dtype float16 --max-log-len 0 --block-size 16 -tp 4 --gpu-memory-utilization 1.0 --model Qwen/Qwen1.5-72B-Chat-AWQ -q awq --max-model-len 14496 --enforce-eager --kv-cache-dtype auto --served-model-name Qwen1.5-72B-Chat-AWQ
Test script:
Result (aphrodite backtrace):
Chat completion works fine if not requesting logprobs. The problem doesn't occur for
v1/completions
, only forv1/chat/completions
. And the gptq Q4 of the same model doesn't have this problem either.The text was updated successfully, but these errors were encountered: