William Zhang ca9537e17c [TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264) ... * Why? Prior to this commit, we only supported a single multimodal input for E/P/D disaggregated serving. * What? This commit does a minor refactor of the multimodal embedding handles that cross process boundaries to enable this. Existing unit tests are updated accordingly to test this. The `RequestOutput` has its `mm_embedding_handle` replaced in favor of `disaggregated_params`, addressing a previous TODO. Signed-off-by: William Zhang <133824995+2ez4bz@users.noreply.github.com>		2026-02-11 20:50:00 -08:00
..
checkpoints	[https://nvbugs/5835925][fix] Add EPD disagg support for Qwen3 VL MoE (#10962)	2026-02-09 23:53:40 +08:00
__init__.py	[None][feat] MiniMax M2 support (#10532)	2026-01-14 17:38:58 +08:00
modeling_auto.py	[TRTC-122][feat] Eagle3 Specdec UX improvements (#10124)	2026-01-22 07:24:11 -08:00
modeling_bert.py	[None][chore] replace print_colored_debug with logger_debug (#8417)	2025-10-22 17:54:38 +08:00
modeling_clip.py	[None][feat] Support kv_cahce_reuse for HyperCLOVAX-Vision model (#7789)	2025-10-21 11:11:24 +09:00
modeling_deepseekv3.py	[TRTLLM-10321][feat] Support different KV cache layout for one-model spec dec (#10502)	2026-02-10 05:16:02 +08:00
modeling_exaone4.py	[https://nvbugs/5569713][fix] Disable fp8 deep gemm for EXAONE-4.0-32B-FP8 (#8429)	2025-11-20 12:43:13 -05:00
modeling_exaone_moe.py	[None][feat] K-EXAONE MTP support (#10796)	2026-01-22 13:43:00 +09:00
modeling_gemma3.py	[#6186][feat] Introduce QKNormRoPEAttention module (#6830)	2025-09-05 14:04:41 +02:00
modeling_gemma3vl.py	[None][fix] Multimodal InputProcessor dummy builder fix (#8916)	2025-11-19 22:32:21 -08:00
modeling_glm.py	[None][fix] Reduce host memory usage during model loading (#11119)	2026-02-05 08:57:40 -08:00
modeling_gpt_oss.py	[None][feat] Support nvfp4 for gptoss (#8956)	2026-01-04 08:57:44 -05:00
modeling_hunyuan_dense.py	[None][fix] Reduce host memory usage during model loading (#11119)	2026-02-05 08:57:40 -08:00
modeling_hunyuan_moe.py	[None][fix] Reduce host memory usage during model loading (#11119)	2026-02-05 08:57:40 -08:00
modeling_hyperclovax.py	[None][fix] Multimodal InputProcessor dummy builder fix (#8916)	2025-11-19 22:32:21 -08:00
modeling_llama_min_latency.py	[https://nvbugs/5803813][fix] Fix llama 4 min latency (#10724)	2026-01-25 18:12:21 +08:00
modeling_llama.py	[TRTLLM-10321][feat] Support different KV cache layout for one-model spec dec (#10502)	2026-02-10 05:16:02 +08:00
modeling_llava_next.py	[TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264)	2026-02-11 20:50:00 -08:00
modeling_minimaxm2.py	[None][feat] MiniMax M2 support (#10532)	2026-01-14 17:38:58 +08:00
modeling_mistral_large3.py	[None][feat] Support Mistral Large3 LLM part (#9820)	2025-12-13 11:44:27 +08:00
modeling_mistral.py	[None][fix] Mistral large 3 few code refine (#10405)	2026-01-08 06:38:49 -05:00
modeling_mixtral.py	[TRTLLM-7408][feat] Wrap MOE with custom op. (#7277)	2025-09-09 12:18:56 -04:00
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	[None][chore] update torch_dtype -> dtype in 'transformers' (#8263)	2025-10-15 17:09:30 +09:00
modeling_multimodal_utils.py	[TRTLLM-8310][feat] Add Qwen3-VL-MoE (#9689)	2025-12-15 20:05:20 -08:00
modeling_nemotron_h.py	[None][chore] Merge residual+hidden into layer norm at the end of each NemotronH MTP, and remove a % operation (#11406)	2026-02-11 12:01:36 -05:00
modeling_nemotron_nano.py	[None][fix] Multimodal InputProcessor dummy builder fix (#8916)	2025-11-19 22:32:21 -08:00
modeling_nemotron_nas.py	[None][feat] add specdec to nemotron nas (#8985)	2025-11-19 19:28:35 +01:00
modeling_nemotron.py	feat: Remove not used padding_idx in models (#5385)	2025-06-25 17:19:59 +08:00
modeling_phi3.py	[https://nvbugs/5540752][fix] Support quantized Phi4 MM models (#8190)	2025-10-20 06:36:09 -04:00
modeling_phi4mm.py	[None][fix] Multimodal InputProcessor dummy builder fix (#8916)	2025-11-19 22:32:21 -08:00
modeling_pixtral.py	[TRTLLM-7442][model] Remove unnecessary D2H copies (#7273)	2025-09-03 23:14:20 -04:00
modeling_qwen2vl.py	[TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264)	2026-02-11 20:50:00 -08:00
modeling_qwen3_moe.py	[TRTLLM-9992][perf] Enable PDL for CuteDSL kernels and overlap MoeOutputMemset (#10043)	2025-12-20 03:12:41 -05:00
modeling_qwen3_next.py	[TRTLLM-10273][feat] Move MambaCacheManager from Python to C++ (#10540)	2026-02-10 07:20:56 -08:00
modeling_qwen3.py	[#4745][fix] Pass lora_params through Qwen2/3 model forward (#10174)	2026-01-07 15:30:17 +08:00
modeling_qwen3vl_moe.py	[https://nvbugs/5835925][fix] Add EPD disagg support for Qwen3 VL MoE (#10962)	2026-02-09 23:53:40 +08:00
modeling_qwen3vl.py	[TRTLLM-10858][feat] Multi-image support for EPD disagg (#11264)	2026-02-11 20:50:00 -08:00
modeling_qwen_moe.py	[TRTLLM-7408][feat] Wrap MOE with custom op. (#7277)	2025-09-09 12:18:56 -04:00
modeling_qwen.py	[#4745][fix] Pass lora_params through Qwen2/3 model forward (#10174)	2026-01-07 15:30:17 +08:00
modeling_radio.py	[TRTLLM-8579][feat] Support quantized model for nano-v2-vlm (#8304)	2025-10-16 09:44:11 +08:00
modeling_seedoss.py	[None][feat] Support Seed-OSS model in pytorch backend (#7496)	2025-09-24 03:57:12 -07:00
modeling_siglip.py	[None][feat] Support kv_cahce_reuse for HyperCLOVAX-Vision model (#7789)	2025-10-21 11:11:24 +09:00
modeling_speculative.py	[TRTLLM-10321][feat] Support different KV cache layout for one-model spec dec (#10502)	2026-02-10 05:16:02 +08:00
modeling_starcoder2.py	[TRTLLM-7967][feat] Adding Starcoder2 PyTorch Backend Support (#8923)	2025-11-24 11:23:22 -08:00
modeling_utils.py	[None][fix] Reduce host memory usage during model loading (#11119)	2026-02-05 08:57:40 -08:00
modeling_vila.py	[None][fix] Multimodal InputProcessor dummy builder fix (#8916)	2025-11-19 22:32:21 -08:00