TensorRT-LLMs/cpp
Daniel Stokes f7c597ec40
[None][perf] Make finalize fusion part of the tactic selection logic (#6915)
Signed-off-by: djns99 <40156487+djns99@users.noreply.github.com>
2025-08-21 14:08:03 -07:00
..
cmake feat: reduce unnecessary kernel generation (#5476) 2025-07-04 14:37:49 +08:00
include/tensorrt_llm [None][chore] No-op changes to support context parallelism in disaggregated serving later (#7063) 2025-08-21 08:21:27 -07:00
kernels [fix]: use safeInitRowMax instead of fp32_lowest to avoid NaN (#7087) 2025-08-20 22:12:21 -07:00
micro_benchmarks [None][perf] Make finalize fusion part of the tactic selection logic (#6915) 2025-08-21 14:08:03 -07:00
tensorrt_llm [None][perf] Make finalize fusion part of the tactic selection logic (#6915) 2025-08-21 14:08:03 -07:00
tests [None][perf] Make finalize fusion part of the tactic selection logic (#6915) 2025-08-21 14:08:03 -07:00
CMakeLists.txt [TRTLLM-7141][infra] Use repo mirrors to avoid intermittent network failures (#6836) 2025-08-15 11:16:07 +08:00
conandata.yml infra: add conan (#3744) 2025-04-30 11:53:14 -07:00
conanfile.py feat: large-scale EP(part 6: Online EP load balancer integration for GB200 nvfp4) (#4818) 2025-06-08 10:25:18 +08:00
libnuma_conan.py fix cuda driver link issue with driver version less than 12.3 (#5025) 2025-06-10 15:27:39 +08:00