Woosuk Kwon d3ea50113c

[V1][Minor] Print KV cache size in token counts (#13596) ...

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

2025-02-20 09:24:31 -08:00

..

__init__.py

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

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

encoder_cache_manager.py

[V1][Bugfix] Copy encoder input ids to fix set iteration issue during VLM abort (#13173)

2025-02-12 12:58:11 -08:00

kv_cache_manager.py

[V1][Spec Decode] Ngram Spec Decode (#12193)

2025-02-15 18:05:11 -08:00

kv_cache_utils.py

[V1][Minor] Print KV cache size in token counts (#13596)

2025-02-20 09:24:31 -08:00

scheduler_output.py

[V1] Get input tokens from scheduler (#13339)

2025-02-17 11:01:07 -08:00

scheduler.py

[V1] Optimize handling of sampling metadata and req_ids list (#13244)

2025-02-18 12:15:33 -08:00