TensorRT-LLMs/examples/auto_deploy/model_registry/configs
2026-02-09 23:26:51 -05:00
..
attn_backend_triton.yaml [None][chore] Update AutoDeploy model list (#10505) 2026-01-10 08:47:37 +02:00
compile_backend_torch_cudagraph.yaml
dashboard_default.yaml
demollm_triton.yaml
gemma3_1b.yaml
glm-4.7-flash.yaml [#11032][feat] MLA revisited and GLM 4.7 Flash support (#11324) 2026-02-09 23:26:51 -05:00
llama3_3_70b.yaml [#10013][feat] AutoDeploy: native cache manager integration (#10635) 2026-01-27 11:23:22 -05:00
llama4_maverick_lite.yaml
llama4_scout.yaml [#10013][feat] AutoDeploy: native cache manager integration (#10635) 2026-01-27 11:23:22 -05:00
multimodal.yaml
num_hidden_layers_5.yaml [None][chore] update model list (#11364) 2026-02-09 21:27:39 +02:00
openelm.yaml
qwen3_vl.yaml [None][chore] update model list (#11364) 2026-02-09 21:27:39 +02:00
simple_shard_only.yaml
world_size_1.yaml
world_size_2.yaml
world_size_4.yaml
world_size_8.yaml