From 7784ac8f913aea30945fb7d5f339c7792ccb0f29 Mon Sep 17 00:00:00 2001 From: Xiaoyu Zhang <1182563586@qq.com> Date: Thu, 30 Jul 2026 22:10:23 +0800 Subject: [PATCH] [diffusion][docs] Fix Cosmos3 model sizes (#32916) --- docs_new/cookbook/diffusion/Cosmos/Cosmos3.mdx | 2 +- docs_new/docs/sglang-diffusion/compatibility_matrix.mdx | 4 ++-- python/sglang/multimodal_gen/registry.py | 2 +- 3 files changed, 4 insertions(+), 4 deletions(-) diff --git a/docs_new/cookbook/diffusion/Cosmos/Cosmos3.mdx b/docs_new/cookbook/diffusion/Cosmos/Cosmos3.mdx index 3bf413cb3..d375b8f25 100644 --- a/docs_new/cookbook/diffusion/Cosmos/Cosmos3.mdx +++ b/docs_new/cookbook/diffusion/Cosmos/Cosmos3.mdx @@ -15,7 +15,7 @@ import { DiffusionModelTags } from '/src/snippets/diffusion/model-tags.jsx'; | Model | Status | Notes | | --- | --- | --- | | `nvidia/Cosmos3-Nano` | Supported | T2I, T2V, I2V, V2V, joint sound, and action | -| `nvidia/Cosmos3-Super` | Supported | T2I, T2V, I2V, and V2V; use multi-GPU for the 32B checkpoint | +| `nvidia/Cosmos3-Super` | Supported | T2I, T2V, I2V, and V2V; use multi-GPU for the 64B checkpoint | | `nvidia/Cosmos3-Super-Text2Image` | Supported | T2I-specialized checkpoint | | `nvidia/Cosmos3-Super-Image2Video` | Supported | I2V-specialized checkpoint | | `nvidia/Cosmos3-Nano-Policy-DROID` | Supported | DROID policy action generation | diff --git a/docs_new/docs/sglang-diffusion/compatibility_matrix.mdx b/docs_new/docs/sglang-diffusion/compatibility_matrix.mdx index a582c14c7..36f977dd0 100644 --- a/docs_new/docs/sglang-diffusion/compatibility_matrix.mdx +++ b/docs_new/docs/sglang-diffusion/compatibility_matrix.mdx @@ -612,8 +612,8 @@ Optimization columns are abbreviated to keep the matrix readable: - `resident` usually provides the best latency/throughput but uses much more VRAM. - Default is auto: `resident` on H200/high-memory CUDA GPUs, otherwise `original`. - Deprecated compatibility: `snapshot` is accepted as an alias for `original` and may be removed after two release cycles. -5. Cosmos3 ships in two sizes — `nvidia/Cosmos3-Nano` (8B) and - `nvidia/Cosmos3-Super` (32B). Both share the same pipeline; the only +5. Cosmos3 ships in two sizes — `nvidia/Cosmos3-Nano` (16B) and + `nvidia/Cosmos3-Super` (64B). Both share the same pipeline; the only difference is transformer depth and width, picked up from `transformer/config.json` at load time. A single checkpoint serves T2V, I2V (`--image-path`), and T2I (`--num-frames 1`). diff --git a/python/sglang/multimodal_gen/registry.py b/python/sglang/multimodal_gen/registry.py index 381b3445e..93c6a6b54 100644 --- a/python/sglang/multimodal_gen/registry.py +++ b/python/sglang/multimodal_gen/registry.py @@ -1035,7 +1035,7 @@ def _register_configs(): # Cosmos3 — single checkpoint serves T2V, I2V, and T2I. Mode is dispatched # per-request inside the pipeline from ``num_frames`` and ``image_path``. - # Both Nano (8B) and Super (32B) share the same pipeline; arch dimensions + # Both Nano (16B) and Super (64B) share the same pipeline; arch dimensions # come from ``transformer/config.json`` via ``update_model_arch``. register_configs( sampling_param_cls=Cosmos3SamplingParams,