Robert Shaw b1340f9d55 [V1] Bugfix: Validate Model Input Length (#12600) ...

SUMMARY:
* avoid crashing the engine when we get an input longer than
max_model_len

FIX #12567(*link existing issues this PR will resolve*)

2025-01-31 18:32:04 -08:00

..

__init__.py

[Core] Support reset_prefix_cache (#12284)

2025-01-22 18:52:27 +00:00

async_llm.py

[V1][Metrics] Add per-request prompt/generation_tokens histograms (#12516)

2025-01-28 22:07:22 +00:00

core_client.py

[Frontend][V1] Online serving performance improvements (#12287)

2025-01-22 22:22:12 +00:00

core.py

[V1] Include Engine Version in Logs (#12496)

2025-01-28 08:27:41 +00:00

detokenizer.py

[V1] [2/n] Logging and Metrics - OutputProcessor Abstraction (#11973)

2025-01-13 04:54:10 +00:00

llm_engine.py

[Core] Support reset_prefix_cache (#12284)

2025-01-22 18:52:27 +00:00

mm_input_mapper.py

[V1] Extend beyond image modality and support mixed-modality inference with Llava-OneVision (#11685)

2025-01-06 19:58:16 +00:00

output_processor.py

[V1][Metrics] Add TTFT and TPOT histograms (#12530)

2025-01-29 04:11:16 +00:00

processor.py

[V1] Bugfix: Validate Model Input Length (#12600)

2025-01-31 18:32:04 -08:00