Commit Graph
10 Commits
Author SHA1 Message Date
roikoren755 72bacc88c8 [NemotronH] Use ReplicatedLinear for fc1_latent_proj (#16569)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-01-14 17:08:27 +08:00
roikoren755 b021332339 [NemotronH] Add latent MoE support (#16227)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-01-02 22:08:58 +08:00
roikoren755 47a660d5b9 [NemotronH] PP support (#16172)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-31 11:16:15 +08:00
roikoren755 de03b0cd30 [Nemotron 3 Nano] Add triton MoE configs (#15815)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-25 19:31:20 +08:00
roikoren755 9003a4369d Add missing assertion in NemotronH path (#15193)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-15 06:17:21 -08:00
roikoren755 3f0482174a Fix Mamba2-based models' default attention backend (#15117)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-14 11:08:48 -08:00
roikoren755 7c985331dd Enable TP for Mamba-based models (#14811)
Signed-off-by: Roi Koren <roik@nvidia.com>
2025-12-10 18:03:50 -08:00
roikoren755 889b46ea50 [Spec] Mamba2 support in target models (#13434) 2025-12-06 00:50:46 +08:00
roikoren755 2ce121a1c3 Enable RadixCache for Mamba2 models (#13584) 2025-12-05 18:23:58 +08:00
roikoren755 1b48e1b974 Feat/nemotron nano v3 support (#12690) 2025-11-21 13:53:05 -08:00