text-generation-inference/integration-tests/models/__snapshots__/test_flash_llama_fp8
Nicolas Patry 85df9fc2db Further fixes. (#2426)
* Further fixes.

* Update the conftest to allow NaN (first logprob).

* Fix the condition.
2024-09-25 06:09:22 +00:00
..
test_flash_llama_fp8_all_params.json fix(server): fix fp8 weight loading (#2268) 2024-09-25 05:31:08 +00:00
test_flash_llama_fp8_load.json Further fixes. (#2426) 2024-09-25 06:09:22 +00:00
test_flash_llama_fp8.json Add FP8 release test (#2261) 2024-09-25 05:29:35 +00:00