Himanshu JajuandNick Hill cd579352bf [V1] Do not detokenize if sampling param detokenize is False (#14224) ...

Signed-off-by: Himanshu Jaju <hj@mistral.ai>
Signed-off-by: Nick Hill <nhill@redhat.com>
Co-authored-by: Nick Hill <nhill@redhat.com>

2025-03-06 10:40:24 -08:00

..

__init__.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

async_llm.py

[V1] Simplify stats logging (#14082)

2025-03-03 10:34:14 -08:00

core_client.py

[V1][BugFix] Fix remaining sync engine client shutdown errors/hangs (#13869)

2025-03-04 15:06:47 +00:00

core.py

[V1] EP/TP MoE + DP Attention (#13931)

2025-03-04 21:27:26 -08:00

detokenizer.py

[V1] Do not detokenize if sampling param detokenize is False (#14224)

2025-03-06 10:40:24 -08:00

llm_engine.py

[V1] Refactor parallel sampling support (#13774)

2025-03-03 08:15:27 -08:00

logprobs.py

[V1] Do not detokenize if sampling param detokenize is False (#14224)

2025-03-06 10:40:24 -08:00

mm_input_cache.py

Update deprecated Python 3.8 typing (#13971)

2025-03-02 17:34:51 -08:00

output_processor.py

[V1] Do not detokenize if sampling param detokenize is False (#14224)

2025-03-06 10:40:24 -08:00

parallel_sampling.py

[WIP][[V1][Metrics] Implement max_num_generation_tokens, request_params_n, and request_params_max_tokens metrics (#14055)

2025-03-03 19:04:45 +00:00

processor.py

Reinstate best_of for V0 (#14356)

2025-03-06 08:34:22 -08:00