Perkz Zheng 1b29c2e731 [None][feat] support gpt-oss with fp8 kv cache (#7612) ... Signed-off-by: Perkz Zheng <67892460+PerkzZheng@users.noreply.github.com>		2025-09-15 02:17:37 +08:00
..
cmake	feat: reduce unnecessary kernel generation (#5476)	2025-07-04 14:37:49 +08:00
include/tensorrt_llm	[None][fix] Fix the incorrect header file import in dataType.h (#7133)	2025-09-11 08:59:04 +08:00
kernels	[TRTLLM-5877][infra] Add fmha tests and auto trigger rules (#6050)	2025-09-09 11:33:09 +08:00
micro_benchmarks	[None][perf] Add MOE support for dynamic cluster shapes and custom epilogue schedules (#6126)	2025-09-02 21:54:43 -04:00
tensorrt_llm	[None][feat] support gpt-oss with fp8 kv cache (#7612)	2025-09-15 02:17:37 +08:00
tests	[None][feat] Nixl support for GDS (#5488)	2025-09-09 13:00:38 +08:00
CMakeLists.txt	[#6529][feat] CMake option to link statically with cublas/curand (#7178)	2025-09-09 14:26:45 +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