roikoren755 b021332339 [NemotronH] Add latent MoE support (#16227) ...

Signed-off-by: Roi Koren <roik@nvidia.com>

2026-01-02 22:08:58 +08:00

..

__init__.py

Support nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 (and nvidia/C-RADIOv2-H) (#12277)

2025-11-26 16:28:52 -07:00

chatglm.py

Revert "fix some typos" (#6244)

2025-05-12 12:53:26 -07:00

dbrx.py

…

deepseek_ocr.py

…

deepseekvl2.py

…

device_config.py

…

dots_ocr.py

…

dots_vlm.py

…

exaone.py

…

falcon_h1.py

move all get_stream in sgl_kernel to c++ to reduce the launch overhead (#12521)

2025-11-02 13:15:05 -08:00

internvl.py

…

janus_pro.py

…

jet_nemotron.py

…

jet_vlm.py

model: support JetVLM (#13289)

2025-11-18 12:02:03 +08:00

kimi_linear.py

…

kimi_vl_moonvit.py

…

kimi_vl.py

…

load_config.py

[Feature] support fastsafetensors (#15091)

2025-12-23 22:33:56 +08:00

longcat_flash.py

…

mamba_utils.py

refactor linear memory pool (#13004)

2025-11-17 16:24:29 +08:00

model_config.py

Separate swa and local attention chunk cache eviction (#15820)

2025-12-26 09:34:22 +08:00

modelopt_config.py

…

nano_nemotron_vl.py

Support nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 (and nvidia/C-RADIOv2-H) (#12277)

2025-11-26 16:28:52 -07:00

nemotron_h.py

[NemotronH] Add latent MoE support (#16227)

2026-01-02 22:08:58 +08:00

olmo3.py

ministral3 (#14251)

2025-12-04 14:31:26 -08:00

points_v15_chat.py

…

qwen3_next.py

ministral3 (#14251)

2025-12-04 14:31:26 -08:00

qwen3_omni.py

[Glm46v] Bug fix for accuracy drop and unable to launch server (#14585)

2025-12-07 23:45:02 -08:00

qwen3_vl.py

[Glm46v] Bug fix for accuracy drop and unable to launch server (#14585)

2025-12-07 23:45:02 -08:00

radio.py

Support nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16 (and nvidia/C-RADIOv2-H) (#12277)

2025-11-26 16:28:52 -07:00

step3_vl.py

…

update_config.py

…

utils.py

…