integration-tests/models/test_flash_gemma_gptq.py · 967ced2ff4565a5358d45a1372d32fbab113700b · OpenDAS / text-generation-inference

Gemma GPTQ checks: skip logprob checks · 967ced2f

Daniël de Kok authored May 30, 2024

This test fails somewhat regularly due to non-determinism and this
test is primarily to verify that we are loading a model which doesn't
have `float16` as the default dtype correctly.

967ced2f

test_flash_gemma_gptq.py 1.76 KB

Replace test_flash_gemma_gptq.py