陈序 218dc2ccda

Aligning top_p and top_k Sampling (#1885) ...

* Align top_p and top_k with huggingface

* remove _get_prompt_and_output_tokens

* rename _apply_top_p_top_k

* compare top_p top_k with hf

* fix test errors

2024-01-12 22:51:03 +01:00

..

test_beam_search.py

Align vLLM's beam search implementation with HF generate (#857)

2023-09-04 17:29:42 -07:00

test_logprobs.py

Implement prompt logprobs & Batched topk for computing logprobs (#1328)

2023-10-16 10:56:50 -07:00

test_rejection_sampler.py

[Speculative decoding 1/9] Optimized rejection sampler (#2336)

2024-01-09 15:38:41 -08:00

test_sampler.py

Aligning top_p and top_k Sampling (#1885)

2024-01-12 22:51:03 +01:00