Shunkangz fd27f89df6 fix: Remove duplicate tokenization in generation server (#4492) ... * Add nvtx Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co> * Add draft change Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co> * Refactor and add support of chat Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co> --------- Signed-off-by: Shunkang <182541032+Shunkangz@users.noreply.github.co> Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>		2025-05-26 16:43:07 +08:00
..
__init__.py	Update TensorRT-LLM (#2873)	2025-03-11 21:13:42 +08:00
executor.py	feat: Support Top-K logprobs and prompt_logprobs in LLMAPI (#3388)	2025-05-01 12:47:14 -04:00
ipc.py	fix: [nvbugs/5066257] serialization improvments (#3869)	2025-05-23 13:06:29 +08:00
postproc_worker.py	fix: [nvbugs/5066257] serialization improvments (#3869)	2025-05-23 13:06:29 +08:00
proxy.py	fix: Remove duplicate tokenization in generation server (#4492)	2025-05-26 16:43:07 +08:00
request.py	feat: Add multimodal embedding field in LlmRequest (#3855)	2025-05-01 12:23:30 +08:00
result.py	[feat][TRTLLM-5018] Dis serving python runtime trt backend (#4243)	2025-05-22 22:01:06 -04:00
serialization.py	fix pipeline tests due to rebase (#4640)	2025-05-26 08:38:08 +08:00
utils.py	fix: llmapi-launch add add trtllm-bench test with engine building (#4091)	2025-05-21 10:18:01 +08:00
worker.py	fix: [nvbugs/5066257] serialization improvments (#3869)	2025-05-23 13:06:29 +08:00