Yuan Luoandluoyuan.luo 53846746bf [VLM] Fix CUDA IPC OOM (#16118) ...

Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>

2026-01-07 11:30:35 +08:00

..

base_processor.py

[VLM] Fix CUDA IPC OOM (#16118)

2026-01-07 11:30:35 +08:00

clip.py

vlm: optimize tensor transport (#6003)

2025-07-26 17:41:01 +08:00

deepseek_ocr.py

model: support deepseek-ocr (#11891)

2025-10-24 03:15:17 +08:00

deepseek_vl_v2.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00

dots_vlm.py

feat: support EPD disaggregation (#12263)

2025-12-14 22:30:08 +08:00

gemma3.py

vlm: optimize tensor transport (#6003)

2025-07-26 17:41:01 +08:00

gemma3n.py

Fix chat template handling for OpenAI serving (#8635)

2025-07-31 21:49:45 -07:00

glm4v.py

[Performance] Replace preprocess_video logic from GLM multimodal processor with transformer impl for speed up (up to 27% faster) and addressing OOM (up to 50x improvements) (#13487)

2025-11-24 18:17:13 -08:00

glmasr.py

fix: change class name of GLM-ASR (#15772)

2025-12-26 00:15:16 +08:00

internvl.py

[VLM] Support request level max_dynamic_patch for OpenAI request (#16268)

2026-01-04 13:04:43 +08:00

janus_pro.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00

kimi_vl.py

vlm: optimize tensor transport (#6003)

2025-07-26 17:41:01 +08:00

llava.py

vlm: refactor engine vlm params and support processor output as input (#14091)

2025-12-20 18:31:24 +08:00

midashenglm.py

Add MiDasheng Model Support (#15219)

2025-12-19 21:41:59 +08:00

minicpm.py

Revert "[VLM] Refactor load_mm_data to improve performance" (#15911)

2025-12-26 13:43:18 -08:00

mlama.py

vlm: optimize tensor transport (#6003)

2025-07-26 17:41:01 +08:00

mllama4.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00

nano_nemotron_vl.py

EVS Framework: Support NemotronH_Nano_VL_V2 (#14051)

2026-01-05 16:18:07 +08:00

nvila.py

model: support JetVLM (#13289)

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

paddleocr_vlm.py

[Model] Add PaddleOCR-VL Model Support (#12953)

2025-12-09 10:16:02 -08:00

phi4mm.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00

pixtral.py

ministral3 (#14251)

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

points_v15_chat.py

fix: duplicate resize images logic of qwen-vl series models (#12458)

2025-11-12 18:08:40 +08:00

qwen_audio.py

fix: fix obsolete qwen-audio processor arg (#9003)

2025-08-09 13:18:36 -07:00

qwen_vl.py

vlm: refactor engine vlm params and support processor output as input (#14091)

2025-12-20 18:31:24 +08:00

sarashina2_vision.py

model support: Sarashina2VisionForCausalLM (#10632)

2025-09-18 17:30:38 -07:00

step3_vl.py

[Lint] Add python/sglang to ruff F401 checks and remove unused imports in files (#11685)

2025-10-17 16:49:46 -07:00