TensorRT-LLMs/cpp
Zongfei Jing 158ebb089c
Remove swizzle for wide ep (#6328)
Signed-off-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
Co-authored-by: Jiang Shao <91270701+StudyingShao@users.noreply.github.com>
2025-07-29 22:59:58 -07:00
..
cmake feat: NIXL interface integration (#3934) 2025-05-19 18:18:22 +08:00
include/tensorrt_llm refactor: remove batch_manager::KvCacheConfig and use executor::KvCacheConfig instead (#5384) 2025-06-26 19:45:52 +08:00
kernels [perf] improve XQA-MLA perf (#5468) 2025-06-26 18:09:13 +08:00
micro_benchmarks Remove swizzle for wide ep (#6328) 2025-07-29 22:59:58 -07:00
tensorrt_llm Remove swizzle for wide ep (#6328) 2025-07-29 22:59:58 -07:00
tests Remove swizzle for wide ep (#6328) 2025-07-29 22:59:58 -07:00
CMakeLists.txt Fix GEMM+AR nvbugs 5219533,5127801,5072306 (#5969) 2025-07-11 10:22:02 -07:00
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