Instructions to use moonshotai/Kimi-K2.5 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use moonshotai/Kimi-K2.5 with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("image-text-to-text", model="moonshotai/Kimi-K2.5", trust_remote_code=True)
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoModel
model = AutoModel.from_pretrained("moonshotai/Kimi-K2.5", trust_remote_code=True, dtype="auto")

Inference
HuggingChat
Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use moonshotai/Kimi-K2.5 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "moonshotai/Kimi-K2.5"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-K2.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker

docker model run hf.co/moonshotai/Kimi-K2.5

SGLang

How to use moonshotai/Kimi-K2.5 with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "moonshotai/Kimi-K2.5" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-K2.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "moonshotai/Kimi-K2.5" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "moonshotai/Kimi-K2.5",
		"messages": [
			{
				"role": "user",
				"content": [
					{
						"type": "text",
						"text": "Describe this image in one sentence."
					},
					{
						"type": "image_url",
						"image_url": {
							"url": "https://cdn.britannica.com/61/93061-050-99147DCE/Statue-of-Liberty-Island-New-York-Bay.jpg"
						}
					}
				]
			}
		]
	}'

Docker Model Runner
How to use moonshotai/Kimi-K2.5 with Docker Model Runner:
```
docker model run hf.co/moonshotai/Kimi-K2.5
```

wangzhengtao commited on Apr 30

Commit

da977e1

1 Parent(s): 54383e8

support transformers inference

Browse files

Files changed (2) hide show

config.json +4 -2
modeling_kimi_k25.py +4 -4

config.json CHANGED Viewed

@@ -116,10 +116,12 @@
       },
       "format": "pack-quantized",
       "ignore": [
-        "lm_head",
         "re:.*self_attn.*",
         "re:.*shared_experts.*",
-        "re:.*mlp\\.(gate|up|gate_up|down)_proj.*"
       ],
       "kv_cache_scheme": null,
       "quant_method": "compressed-tensors",

       },
       "format": "pack-quantized",
       "ignore": [
         "re:.*self_attn.*",
         "re:.*shared_experts.*",
+        "re:.*mlp\\.(gate|up|gate_up|down)_proj.*",
+        "re:.*lm_head.*",
+        "re:vision_tower.*",
+        "re:mm_projector.*"
       ],
       "kv_cache_scheme": null,
       "quant_method": "compressed-tensors",

modeling_kimi_k25.py CHANGED Viewed

@@ -562,7 +562,8 @@ class MoonViT3dEncoder(nn.Module):
                  hidden_dim: int,
                  num_layers: int,
                  block_cfg: dict,
-                 video_attn_type: str = 'spatial_temporal') -> None:
         super().__init__()
         assert video_attn_type == 'spatial_temporal', f'video_attn_type must be "spatial_temporal", got {video_attn_type}'
@@ -570,9 +571,8 @@ class MoonViT3dEncoder(nn.Module):
         self.rope_2d = Rope2DPosEmbRepeated(
             block_cfg['hidden_dim'] // block_cfg['num_heads'], 512, 512)
         self.blocks = nn.ModuleList([
-            MoonViTEncoderLayer(
-                **block_cfg,
-                use_deterministic_attn=self.use_deterministic_attn)
             for _ in range(num_layers)
         ])
         self.final_layernorm = nn.LayerNorm(hidden_dim)

                  hidden_dim: int,
                  num_layers: int,
                  block_cfg: dict,
+                 video_attn_type: str = 'spatial_temporal',
+                 use_deterministic_attn: bool = False) -> None:
         super().__init__()
         assert video_attn_type == 'spatial_temporal', f'video_attn_type must be "spatial_temporal", got {video_attn_type}'
         self.rope_2d = Rope2DPosEmbRepeated(
             block_cfg['hidden_dim'] // block_cfg['num_heads'], 512, 512)
         self.blocks = nn.ModuleList([
+            MoonViTEncoderLayer(**block_cfg,
+                                use_deterministic_attn=use_deterministic_attn)
             for _ in range(num_layers)
         ])
         self.final_layernorm = nn.LayerNorm(hidden_dim)