Nick Hill 05fcd1b430 [V1][Perf] Faster incremental detokenization (#15137) ...

Signed-off-by: Nick Hill <nhill@redhat.com>

2025-04-17 07:45:24 -07:00

..

__init__.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

async_llm.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

core_client.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

core.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

detokenizer.py

[V1][Perf] Faster incremental detokenization (#15137)

2025-04-17 07:45:24 -07:00

exceptions.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -07:00

llm_engine.py

Add "/server_info" endpoint in api_server to retrieve the vllm_config.  (#16572)

2025-04-15 11:50:38 +00:00

logprobs.py

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

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

mm_input_cache.py

[Bugfix] Multi-modal caches not acting like LRU caches (#16593)

2025-04-14 09:24:16 -07:00

output_processor.py

[V1][Frontend] Improve Shutdown And Logs (#11737)

2025-04-16 19:48:34 -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] Revert max_prompt_len validation for decoder-only models. (#16741)

2025-04-16 21:33:15 -07:00