Cyrus Leung 4ebc0b9640 [Bugfix] Proper input validation for multi-modal encoder-decoder models (#16156) ...

Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>

2025-04-08 09:45:21 -07:00

..

__init__.py

[V1] AsyncLLM data parallel (#13923)

2025-03-27 16:14:41 -07:00

async_llm.py

[core] Add tags parameter to wake_up() (#15500)

2025-04-02 01:59:27 -07:00

core_client.py

[V1][BugFix] Exit properly if engine core fails during startup (#16137)

2025-04-07 15:30:15 -07:00

core.py

[V1] DP scale-out (1/N): Use zmq ROUTER/DEALER sockets for input queue (#15906)

2025-04-04 12:56:43 -07:00

detokenizer.py

[V1] Detokenizer: Respect Stop Tokens + not include_stop_str_in_output (#14624)

2025-03-13 19:07:34 +00:00

llm_engine.py

[core] Add tags parameter to wake_up() (#15500)

2025-04-02 01:59:27 -07:00

logprobs.py

[V1] Aggregate chunked prompt logprobs in model runner (#14875)

2025-03-24 12:27:57 -04:00

mm_input_cache.py

[V1] Remove input cache client (#14864)

2025-03-16 23:42:06 -07:00

output_processor.py

[Misc][V1] Misc code streamlining (#15723)

2025-03-28 20:59:47 -07:00

parallel_sampling.py

[V1] Avoid redundant input processing in n>1 case (#14985)

2025-03-20 22:24:10 -07:00

processor.py

[Bugfix] Proper input validation for multi-modal encoder-decoder models (#16156)

2025-04-08 09:45:21 -07:00