WeiHaocheng dccbfc8b1e fix: Set init value for moe expert id (#5660) ... Signed-off-by: Fred Wei <20514172+WeiHaocheng@users.noreply.github.com>		2025-07-03 07:05:31 -04:00
..
cmake	feat: NIXL interface integration (#3934)	2025-05-19 18:18:22 +08:00
include/tensorrt_llm	refactor: Clean up DecodingInput and DecodingOutput (#5617)	2025-07-01 14:31:42 +02:00
kernels	[#5403][perf] Conditionally enable SWAP AB for speculative decoding (#5404)	2025-07-01 18:32:37 +08:00
micro_benchmarks	feat: Add support for per expert activation scaling factors (#5013)	2025-06-28 09:10:35 +12:00
tensorrt_llm	fix: Set init value for moe expert id (#5660)	2025-07-03 07:05:31 -04:00
tests	[TRTLLM-1316] refactor: Remove unnecessary pipeline parallelism logic from postProcessRequest (#5489)	2025-07-02 10:13:31 +02:00
CMakeLists.txt	Fix execute_process: check results using EQUAL (#5481)	2025-06-27 11:57:04 +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