Kunshang JiandHarry Mellor 16d2ad1d38 [Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681) ...

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
Signed-off-by: Kunshang Ji <jikunshang95@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>

2026-03-04 09:49:47 +00:00

..

logits_processor

[Core] Support min_tokens with speculative decoding (#32642)

2026-02-26 12:31:28 -05:00

ops

[Hardware] Replace torch.cuda.empty_cache with torch.accelerator.empty_cache (#30681)

2026-03-04 09:49:47 +00:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

metadata.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

rejection_sampler.py

[cohere][fix][spec-decode]: fix crash when allowed_token_ids is set without penalties (#35654)

2026-03-03 23:20:15 -08:00

sampler.py

Fix num_logprobs parameter description in sampler.py (#34451)

2026-02-12 18:18:03 -08:00