vllm/tests/spec_decode
2024-05-01 19:24:13 -07:00
..
e2e [Speculative decoding] Add ngram prompt lookup decoding (#4237) 2024-05-01 11:13:03 -07:00
__init__.py [Speculative decoding 3/9] Worker which speculates, scores, and applies rejection sampling (#3103) 2024-03-08 23:32:46 -08:00
test_batch_expansion.py [Misc] Add pytest marker to opt-out of global test cleanup (#3863) 2024-04-04 21:54:16 -07:00
test_metrics.py [Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951) 2024-04-23 08:02:36 +00:00
test_multi_step_worker.py [Speculative decoding] Add ngram prompt lookup decoding (#4237) 2024-05-01 11:13:03 -07:00
test_ngram_worker.py [Speculative decoding] Add ngram prompt lookup decoding (#4237) 2024-05-01 11:13:03 -07:00
test_spec_decode_worker.py [Bug fix][Core] assert num_new_tokens == 1 fails when SamplingParams.n is not 1 and max_tokens is large & Add tests for preemption (#4451) 2024-05-01 19:24:13 -07:00
test_utils.py [CI] Try introducing isort. (#3495) 2024-03-25 07:59:47 -07:00
utils.py [Speculative decoding 7/9] Speculative decoding end-to-end correctness tests. (#3951) 2024-04-23 08:02:36 +00:00