Yao Yao 0788c5d0d6 [perf] improve XQA-MLA perf (#5468) ... Signed-off-by: Yao Yao <lowsfer@users.noreply.github.com>		2025-06-26 18:09:13 +08:00
..
cmake	feat: NIXL interface integration (#3934)	2025-05-19 18:18:22 +08:00
include/tensorrt_llm	opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222)	2025-06-26 12:18:19 +08:00
kernels	[perf] improve XQA-MLA perf (#5468)	2025-06-26 18:09:13 +08:00
micro_benchmarks	opensource: Opensource MOE MXFP8-MXFP4 implementation (#5222)	2025-06-26 12:18:19 +08:00
tensorrt_llm	perf: Optimize swizzle_sf, unswizzle_sf, reswizzle_sf (#5318)	2025-06-26 14:03:56 +08:00
tests	feat: large-scale EP(part 8: Online EP load balancer integration for PCIe fp8) (#5226)	2025-06-25 22:25:13 -07:00
CMakeLists.txt	[chore] Allow configuring linking of NVRTC wrapper (#5189)	2025-06-26 07:26:10 +02:00
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