| .. |
|
__init__.py
|
feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799)
|
2025-06-09 11:04:04 +08:00 |
|
.gitkeep
|
Update TensorRT-LLM (#2755)
|
2025-02-11 03:01:00 +00:00 |
|
modeling_auto.py
|
[Arch] Freeze model_config (#4814)
|
2025-06-04 02:51:35 +08:00 |
|
modeling_bert.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_clip.py
|
Cherry pick feat/llama4 to main (#4739)
|
2025-05-30 05:28:40 +08:00 |
|
modeling_deepseekv3.py
|
Use backend to replace macro to control enablement of MNNVL all reduce (#4635)
|
2025-06-12 11:22:49 +08:00 |
|
modeling_gemma3.py
|
chore: Refactor apply_rope. (#4918)
|
2025-06-09 16:51:59 +08:00 |
|
modeling_hyperclovax.py
|
feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799)
|
2025-06-09 11:04:04 +08:00 |
|
modeling_llama_min_latency.py
|
[fix] Fix llama4 min latency (#5117)
|
2025-06-11 15:44:38 +08:00 |
|
modeling_llama.py
|
[nvbug/5334370][fix] Fix one model EAGLE3 (#5134)
|
2025-06-12 10:28:14 -04:00 |
|
modeling_llava_next.py
|
feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799)
|
2025-06-09 11:04:04 +08:00 |
|
modeling_mamba_hybrid.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_mistral.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_mixtral.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_mllama.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_multimodal_encoder.py
|
Update TensorRT-LLM (#2873)
|
2025-03-11 21:13:42 +08:00 |
|
modeling_multimodal_utils.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_nemotron_h.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_nemotron_nas.py
|
Use backend to replace macro to control enablement of MNNVL all reduce (#4635)
|
2025-06-12 11:22:49 +08:00 |
|
modeling_nemotron.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_qwen2vl.py
|
[TRTLLM-5007][feat] Add multimodal hashing support (image hashing) (#4145)
|
2025-06-10 01:59:56 +08:00 |
|
modeling_qwen3_moe.py
|
Use backend to replace macro to control enablement of MNNVL all reduce (#4635)
|
2025-06-12 11:22:49 +08:00 |
|
modeling_qwen3.py
|
chore: Refactor apply_rope. (#4918)
|
2025-06-09 16:51:59 +08:00 |
|
modeling_qwen_moe.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_qwen.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_siglip.py
|
Cherry pick feat/llama4 to main (#4739)
|
2025-05-30 05:28:40 +08:00 |
|
modeling_utils.py
|
chore: Change the type annotations of input_ids and position_ids to int32. (#4632)
|
2025-06-07 16:10:47 +08:00 |
|
modeling_vila.py
|
feat: add HyperCLOVAX-SEED-Vision support in refactored way (#4799)
|
2025-06-09 11:04:04 +08:00 |
