Woosuk KwonandGitHub 99abb8b650 [V1][Spec Decode] Optimize Rejection Sampler with Triton Kernels (#14930) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-03-18 14:31:54 -07:00

..

__init__.py

[V1] Adding min tokens/repetition/presence/frequence penalties to V1 sampler (#10681)

2024-12-26 19:02:58 +09:00

test_logprobs_e2e.py

Consolidate Llama model usage in tests (#13094)

2025-02-13 22:18:03 -08:00

test_logprobs.py

[Misc] Replace os environ to monkeypatch in test suite (#14516)

2025-03-16 20:35:57 -07:00

test_rejection_sampler.py

[V1][Spec Decode] Optimize Rejection Sampler with Triton Kernels (#14930)

2025-03-18 14:31:54 -07:00

test_sampler.py

[V1] Support bad_words in sampler (#13376)

2025-03-08 14:50:26 -08:00

test_sampling_params_e2e.py

[V1] Support bad_words in sampler (#13376)

2025-03-08 14:50:26 -08:00

utils.py

[V1] Prompt logprobs + APC compatibility; prompt logprobs reqs cannot fill APC (#13949)

2025-03-08 01:48:12 +00:00