Matthias Jouanneaux 1be7faef37 [TRTLLM-5966][feat] Helix: add custom position ids to MLA kernels (#6904) ... Signed-off-by: Matthias Jouanneaux <mjoux@nvidia.com> Co-authored-by: brb-nv <169953907+brb-nv@users.noreply.github.com>		2025-09-19 20:55:32 +08:00
..
batch_manager	[None][fix] using arrival time in llmapi when creating LlmRequest in pytorch workflow (#7553)	2025-09-15 07:26:01 -04:00
common	[None][feat] Add Request specific exception (#6931)	2025-09-04 18:43:42 -04:00
executor	[https://nvbugs/5477359][fix] Nanobind: Allow none types for fields in result (#7672)	2025-09-10 14:13:46 +01:00
runtime	[https://nvbugs/5489015][fix] Support communicator split in MNNVL allreduce and fix the binding issues. (#7387)	2025-09-17 07:43:20 +08:00
testing	feat: nanobind bindings (#6185)	2025-07-21 08:56:57 +01:00
thop	[TRTLLM-5966][feat] Helix: add custom position ids to MLA kernels (#6904)	2025-09-19 20:55:32 +08:00
userbuffers	[TRTLLM-7028][feat] Enable guided decoding with speculative decoding (part 2: one-model engine) (#6948)	2025-09-03 15:16:11 -07:00
bindings.cpp	[None][fix] using arrival time in llmapi when creating LlmRequest in pytorch workflow (#7553)	2025-09-15 07:26:01 -04:00
CMakeLists.txt	[None][feat] Add Request specific exception (#6931)	2025-09-04 18:43:42 -04:00