Cheng Hang cdce68c3e0 [TRTLLM-6741][fix] Add heuristics for lm head tp size when enable_lm_head_tp_in_adp=True (#7891) ... Signed-off-by: Cheng Hang <chang@nvidia.com> Co-authored-by: Yanchao Lu <yanchaol@nvidia.com>		2025-09-30 09:24:35 +08:00
..
docker	infra: [TRTLLM-5247][TRTLLM-5248][TRTLLM-5249] Refactor docker build image groovy and support NGC images (#4294)	2025-05-29 11:23:29 +08:00
scripts	[TRTLLM-6295][test] Exit as early as possible and propagate exit status correctly for multi-node testing (#7739)	2025-09-16 09:59:18 +08:00
Build.groovy	[TRTLLM-6106][feat] Add support for KVCache transfer from KVCache reuse path (#6348)	2025-09-27 19:29:30 -04:00
BuildDockerImage.groovy	[None][ci] Some improvements for Slurm CI (#7689)	2025-09-14 16:56:32 +08:00
controlCCache.groovy	[https://nvbugs/5415862][fix] Update cublas as 12.9.1 and cuda memory alignment as 256 (#6501)	2025-08-15 11:10:59 +08:00
current_image_tags.properties	[TRTLLM-4629] [feat] Add support of CUDA13 and sm103 devices (#7568)	2025-09-16 09:56:18 +08:00
GenerateLock.groovy	[None][infra] Add nightly pipeline to generate lock files (#5798)	2025-09-16 15:00:03 -07:00
L0_MergeRequest.groovy	[None][feat] Enable gpt oss on DGX H100. (#6775)	2025-09-23 09:35:19 -07:00
L0_Test.groovy	[TRTLLM-6741][fix] Add heuristics for lm head tp size when enable_lm_head_tp_in_adp=True (#7891)	2025-09-30 09:24:35 +08:00
license_cpp.json	Refactor: move DeepEP from Docker images to wheel building (#5534)	2025-07-07 22:57:03 +09:00