..
checkpoints
Deepseek R1 FP8 Support on Blackwell ( #6486 )
2025-08-01 10:26:28 +08:00
__init__.py
[fix] Fix Mistral3VLM weight-loading & enable in pre-merge ( #6105 )
2025-07-17 11:04:17 -07:00
modeling_auto.py
[feat] Implement model-agnostic one-engine eagle3 ( #4778 )
2025-06-13 08:11:41 -07:00
modeling_bert.py
feat: Remove not used padding_idx in models ( #5385 )
2025-06-25 17:19:59 +08:00
modeling_clip.py
[feat] Enable TP and batching for PixtralVisionModel / Mistral3VLM ( #6152 )
2025-07-22 11:06:41 -07:00
modeling_deepseekv3.py
Deepseek R1 FP8 Support on Blackwell ( #6486 )
2025-08-01 10:26:28 +08:00
modeling_exaone4.py
feat: EXAONE4.0 support ( #5696 )
2025-07-14 22:28:10 +09:00
modeling_gemma3.py
fix: Fix poor generation with FP8 Gemma3 1B checkpoint ( #6499 )
2025-07-31 17:18:23 -07:00
modeling_gemma3vl.py
fix: support mixture of text & multimodal prompts ( #6345 )
2025-07-30 08:52:31 +08:00
modeling_hyperclovax.py
fix: support mixture of text & multimodal prompts ( #6345 )
2025-07-30 08:52:31 +08:00
modeling_llama_min_latency.py
[Model load] Fix llama min-latency model load ( #5883 )
2025-07-15 09:29:19 +08:00
modeling_llama.py
[TRTLLM-6654][feat] Add support for external multimodal embeddings ( #6263 )
2025-07-30 10:00:15 -04:00
modeling_llava_next.py
[TRTLLM-6654][feat] Add support for external multimodal embeddings ( #6263 )
2025-07-30 10:00:15 -04:00
modeling_mistral.py
fix: support mixture of text & multimodal prompts ( #6345 )
2025-07-30 08:52:31 +08:00
modeling_mixtral.py
feat: Remove padding in attention DP. ( #6064 )
2025-07-18 23:30:34 +08:00
modeling_mllama.py
feat : support duplicate_kv_weight for qwen3 blockwise scale ( #5459 )
2025-06-30 11:49:22 +08:00
modeling_multimodal_encoder.py
Update TensorRT-LLM ( #2873 )
2025-03-11 21:13:42 +08:00
modeling_multimodal_utils.py
[TRTLLM-5059][feat] Add KV cache reuse support for multimodal models ( #5444 )
2025-07-21 16:11:58 -07:00
modeling_nemotron_h.py
[TRTLLM-5493] Add core infrastructure to enable loading of custom checkpoint formats ( #5372 )
2025-07-17 00:50:30 +08:00
modeling_nemotron_nas.py
[Perf]: Add residual, norm for nemotron_nas models ( #6455 )
2025-07-30 09:10:38 -07:00
modeling_nemotron.py
feat: Remove not used padding_idx in models ( #5385 )
2025-06-25 17:19:59 +08:00
modeling_phi3.py
feat: TRTLLM-6450 update long rope for phi3.5/phi4-mini/phi4-mm ( #6353 )
2025-07-30 09:20:16 -07:00
modeling_phi4mm.py
[5830][feat] Improve LoRA cache memory control ( #6220 )
2025-07-31 09:26:38 +03:00
modeling_pixtral.py
[feat] Enable TP and batching for PixtralVisionModel / Mistral3VLM ( #6152 )
2025-07-22 11:06:41 -07:00
modeling_qwen2vl.py
[PERF] Move calculation Qwen2-VL's rotary_cos_sin to LLM worker process ( #6004 )
2025-07-31 09:35:24 +09:00
modeling_qwen3_moe.py
[Fix][nvbug 5401163][nvbug 5404726][Qwen3] Fix bug of MoE on tp > 1 with trtllm moe backend ( #6235 )
2025-07-24 21:47:37 +08:00
modeling_qwen3.py
feat(eagle3):support qwen3 dense model ( #5879 )
2025-07-19 01:24:32 +08:00
modeling_qwen_moe.py
[TRTLLM-5493] Add core infrastructure to enable loading of custom checkpoint formats ( #5372 )
2025-07-17 00:50:30 +08:00
modeling_qwen.py
feat: Remove not used padding_idx in models ( #5385 )
2025-06-25 17:19:59 +08:00
modeling_siglip.py
feat: Update Gemma3 Vision Encoder ( #5973 )
2025-07-14 22:38:10 +08:00
modeling_speculative.py
Mtp optimizations round1 ( #5689 )
2025-07-25 13:48:27 -04:00
modeling_utils.py
[Fix][nvbug 5401163][nvbug 5404726][Qwen3] Fix bug of MoE on tp > 1 with trtllm moe backend ( #6235 )
2025-07-24 21:47:37 +08:00
modeling_vila.py
fix: support mixture of text & multimodal prompts ( #6345 )
2025-07-30 08:52:31 +08:00
7bb0a78631