minke.yu/sglang
1
0
Fork 0
Code Issues Pull Requests Actions 12 Packages Projects Releases Wiki Activity

Add Lychee Doc Links Check to Local and CI (#19742)

Browse Source 
Co-authored-by: Zijie Xia <zijie_xia@icloud.com>
Co-authored-by: Zijie Xia <zijiexia@users.noreply.github.com>
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com>
This commit is contained in:
Jiaxin(Jackson) Deng
2026-03-24 13:48:26 -07:00
committed by GitHub
co-authored by Zijie Xia Zijie Xia zijiexia
parent a32e0d57e7
commit c4db64c16b
25 changed files with 154 additions and 32 deletions
Download Patch File Download Diff File Expand all files Collapse all files
docs/supported_models/text_generation/multimodal_language_models.md
+1 -1
View File
@@ -63,7 +63,7 @@ SGLang supports video input for Vision-Language Models (VLMs), enabling temporal
| **GLM-4v** (4.5V, 4.1V, MOE) | `zai-org/GLM-4.5V` | Video clips are read with Decord, converted to tensors, and passed to the model alongside metadata for rotary-position handling. |
| **NVILA** (Full & Lite) | `Efficient-Large-Model/NVILA-8B` | The runtime samples eight frames per clip and attaches them to the multimodal request when `video_data` is present. |
| **LLaVA video variants** (LLaVA-NeXT-Video, LLaVA-OneVision) | `lmms-lab/LLaVA-NeXT-Video-7B` | The processor routes video prompts to the LlavaVid video-enabled architecture, and the provided example shows how to query it with `sgl.video(...)` clips. |
| **NVIDIA Nemotron Nano 2.0 VL** | `nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16` | The processor samples at 2 FPS, at a max of 128 frames, as per model training. The model uses [EVS](../../python/sglang/srt/multimodal/evs/README.md), a pruning method that removes redundant tokens from video embeddings. By default `video_pruning_rate=0.7`. Change this by providing: `--json-model-override-args '{"video_pruning_rate": 0.0}'` to disable EVS, for example. |
| **NVIDIA Nemotron Nano 2.0 VL** | `nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL-BF16` | The processor samples at 2 FPS, at a max of 128 frames, as per model training. The model uses [EVS](../../../python/sglang/srt/multimodal/evs/README.md), a pruning method that removes redundant tokens from video embeddings. By default `video_pruning_rate=0.7`. Change this by providing: `--json-model-override-args '{"video_pruning_rate": 0.0}'` to disable EVS, for example. |
| **JetVLM** | | The runtime samples eight frames per clip and attaches them to the multimodal request when `video_data` is present. |
Use `sgl.video(path, num_frames)` when building prompts to attach clips from your SGLang programs.