Robin Kobus 502758aaa9 fix: Handle additional model outputs based on pipeline parallel rank (#4498) ... - Only allocate additional outputs on last pipeline parallel rank in trtGptModelInflightBatching and executorImpl. Signed-off-by: Robin Kobus <19427718+Funatiq@users.noreply.github.com>		2025-05-26 09:04:40 +02:00
..
cmake	feat: NIXL interface integration (#3934)	2025-05-19 18:18:22 +08:00
include/tensorrt_llm	sort llm request state (#4607)	2025-05-26 13:47:01 +08:00
kernels	fix: rename some terms (#4534)	2025-05-23 23:23:49 +08:00
micro_benchmarks	feat: support add internal cutlass kernels as subproject (#3658)	2025-05-06 11:35:07 +08:00
tensorrt_llm	fix: Handle additional model outputs based on pipeline parallel rank (#4498)	2025-05-26 09:04:40 +02:00
tests	refactor: CreateNewDecoderRequests (#4452)	2025-05-23 22:54:37 +08:00
CMakeLists.txt	fix: better method to help torch find nvtx3 (#4110)	2025-05-15 16:42:30 +08:00
conandata.yml	infra: add conan (#3744)	2025-04-30 11:53:14 -07:00
conanfile.py	infra: add conan (#3744)	2025-04-30 11:53:14 -07:00