text-generation-inference/integration-tests/models/__snapshots__/test_grammar_llama
drbh d4aebbd10a fix: correctly index into mask when applying grammar (#1618)
This PR fixes how the grammar mask is index when generating text and
adds a new test to ensure the grammars work with non flash models
2024-04-25 10:16:16 +03:00
..
test_non_flash_llama_grammar_json.json fix: correctly index into mask when applying grammar (#1618) 2024-04-25 10:16:16 +03:00