Instructions to use bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 with Transformers:

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

pipe = pipeline("image-text-to-text", model="bottlecapai/ThinkingCap-Qwen3.6-27B-FP8")
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 AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("bottlecapai/ThinkingCap-Qwen3.6-27B-FP8")
model = AutoModelForMultimodalLM.from_pretrained("bottlecapai/ThinkingCap-Qwen3.6-27B-FP8", device_map="auto")
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?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8",
		"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/bottlecapai/ThinkingCap-Qwen3.6-27B-FP8

SGLang

How to use bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 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 "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8" \
    --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": "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8",
		"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 "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8" \
        --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": "bottlecapai/ThinkingCap-Qwen3.6-27B-FP8",
		"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 bottlecapai/ThinkingCap-Qwen3.6-27B-FP8 with Docker Model Runner:
```
docker model run hf.co/bottlecapai/ThinkingCap-Qwen3.6-27B-FP8
```

Fix for vLLM Loading Crash on Ampere/Ada GPUs (TP=8, RuntimeError: size_n = 12)

by MadGoatHaz - opened 13 days ago

Discussion

MadGoatHaz

13 days ago

•

edited 13 days ago

Cant seem to get this working - but I at least was able to get it to load using this (my last attempt) script. (see below) - I at this point think the MTP heads / weights are messed up in a way that it's impossible to get MTP working correctly in vllm.

{
"architectures": [
"Qwen3_5ForConditionalGeneration"
],
"dtype": "bfloat16",
"image_token_id": 248056,
"language_model_only": false,
"model_type": "qwen3_5",
"quantization_config": {
"config_groups": {
"group_0": {
"format": "float-quantized",
"input_activations": {
"actorder": null,
"block_structure": null,
"dynamic": true,
"group_size": null,
"num_bits": 8,
"observer": null,
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "token",
"symmetric": true,
"type": "float",
"zp_dtype": null
},
"output_activations": null,
"targets": [
"Linear"
],
"weights": {
"actorder": null,
"block_structure": null,
"dynamic": false,
"group_size": null,
"num_bits": 8,
"observer": "memoryless_minmax",
"observer_kwargs": {},
"scale_dtype": null,
"strategy": "channel",
"symmetric": true,
"type": "float",
"zp_dtype": null
}
}
},
"format": "float-quantized",
"global_compression_ratio": null,
"ignore": [
"model.visual.blocks.0.attn.qkv",
"model.visual.blocks.0.attn.proj",
"model.visual.blocks.0.mlp.linear_fc1",
"model.visual.blocks.0.mlp.linear_fc2",
"model.visual.blocks.1.attn.qkv",
"model.visual.blocks.1.attn.proj",
"model.visual.blocks.1.mlp.linear_fc1",
"model.visual.blocks.1.mlp.linear_fc2",
"model.visual.blocks.2.attn.qkv",
"model.visual.blocks.2.attn.proj",
"model.visual.blocks.2.mlp.linear_fc1",
"model.visual.blocks.2.mlp.linear_fc2",
"model.visual.blocks.3.attn.qkv",
"model.visual.blocks.3.attn.proj",
"model.visual.blocks.3.mlp.linear_fc1",
"model.visual.blocks.3.mlp.linear_fc2",
"model.visual.blocks.4.attn.qkv",
"model.visual.blocks.4.attn.proj",
"model.visual.blocks.4.mlp.linear_fc1",
"model.visual.blocks.4.mlp.linear_fc2",
"model.visual.blocks.5.attn.qkv",
"model.visual.blocks.5.attn.proj",
"model.visual.blocks.5.mlp.linear_fc1",
"model.visual.blocks.5.mlp.linear_fc2",
"model.visual.blocks.6.attn.qkv",
"model.visual.blocks.6.attn.proj",
"model.visual.blocks.6.mlp.linear_fc1",
"model.visual.blocks.6.mlp.linear_fc2",
"model.visual.blocks.7.attn.qkv",
"model.visual.blocks.7.attn.proj",
"model.visual.blocks.7.mlp.linear_fc1",
"model.visual.blocks.7.mlp.linear_fc2",
"model.visual.blocks.8.attn.qkv",
"model.visual.blocks.8.attn.proj",
"model.visual.blocks.8.mlp.linear_fc1",
"model.visual.blocks.8.mlp.linear_fc2",
"model.visual.blocks.9.attn.qkv",
"model.visual.blocks.9.attn.proj",
"model.visual.blocks.9.mlp.linear_fc1",
"model.visual.blocks.9.mlp.linear_fc2",
"model.visual.blocks.10.attn.qkv",
"model.visual.blocks.10.attn.proj",
"model.visual.blocks.10.mlp.linear_fc1",
"model.visual.blocks.10.mlp.linear_fc2",
"model.visual.blocks.11.attn.qkv",
"model.visual.blocks.11.attn.proj",
"model.visual.blocks.11.mlp.linear_fc1",
"model.visual.blocks.11.mlp.linear_fc2",
"model.visual.blocks.12.attn.qkv",
"model.visual.blocks.12.attn.proj",
"model.visual.blocks.12.mlp.linear_fc1",
"model.visual.blocks.12.mlp.linear_fc2",
"model.visual.blocks.13.attn.qkv",
"model.visual.blocks.13.attn.proj",
"model.visual.blocks.13.mlp.linear_fc1",
"model.visual.blocks.13.mlp.linear_fc2",
"model.visual.blocks.14.attn.qkv",
"model.visual.blocks.14.attn.proj",
"model.visual.blocks.14.mlp.linear_fc1",
"model.visual.blocks.14.mlp.linear_fc2",
"model.visual.blocks.15.attn.qkv",
"model.visual.blocks.15.attn.proj",
"model.visual.blocks.15.mlp.linear_fc1",
"model.visual.blocks.15.mlp.linear_fc2",
"model.visual.blocks.16.attn.qkv",
"model.visual.blocks.16.attn.proj",
"model.visual.blocks.16.mlp.linear_fc1",
"model.visual.blocks.16.mlp.linear_fc2",
"model.visual.blocks.17.attn.qkv",
"model.visual.blocks.17.attn.proj",
"model.visual.blocks.17.mlp.linear_fc1",
"model.visual.blocks.17.mlp.linear_fc2",
"model.visual.blocks.18.attn.qkv",
"model.visual.blocks.18.attn.proj",
"model.visual.blocks.18.mlp.linear_fc1",
"model.visual.blocks.18.mlp.linear_fc2",
"model.visual.blocks.19.attn.qkv",
"model.visual.blocks.19.attn.proj",
"model.visual.blocks.19.mlp.linear_fc1",
"model.visual.blocks.19.mlp.linear_fc2",
"model.visual.blocks.20.attn.qkv",
"model.visual.blocks.20.attn.proj",
"model.visual.blocks.20.mlp.linear_fc1",
"model.visual.blocks.20.mlp.linear_fc2",
"model.visual.blocks.21.attn.qkv",
"model.visual.blocks.21.attn.proj",
"model.visual.blocks.21.mlp.linear_fc1",
"model.visual.blocks.21.mlp.linear_fc2",
"model.visual.blocks.22.attn.qkv",
"model.visual.blocks.22.attn.proj",
"model.visual.blocks.22.mlp.linear_fc1",
"model.visual.blocks.22.mlp.linear_fc2",
"model.visual.blocks.23.attn.qkv",
"model.visual.blocks.23.attn.proj",
"model.visual.blocks.23.mlp.linear_fc1",
"model.visual.blocks.23.mlp.linear_fc2",
"model.visual.blocks.24.attn.qkv",
"model.visual.blocks.24.attn.proj",
"model.visual.blocks.24.mlp.linear_fc1",
"model.visual.blocks.24.mlp.linear_fc2",
"model.visual.blocks.25.attn.qkv",
"model.visual.blocks.25.attn.proj",
"model.visual.blocks.25.mlp.linear_fc1",
"model.visual.blocks.25.mlp.linear_fc2",
"model.visual.blocks.26.attn.qkv",
"model.visual.blocks.26.attn.proj",
"model.visual.blocks.26.mlp.linear_fc1",
"model.visual.blocks.26.mlp.linear_fc2",
"model.visual.merger.linear_fc1",
"model.visual.merger.linear_fc2",
"lm_head",
"model.language_model.layers.0.linear_attn.in_proj_ba",
"model.language_model.layers.0.linear_attn.in_proj_b",
"model.language_model.layers.0.linear_attn.in_proj_a",
"model.language_model.layers.0.linear_attn.in_proj_qkvz",
"model.language_model.layers.1.linear_attn.in_proj_ba",
"model.language_model.layers.1.linear_attn.in_proj_b",
"model.language_model.layers.1.linear_attn.in_proj_a",
"model.language_model.layers.1.linear_attn.in_proj_qkvz",
"model.language_model.layers.2.linear_attn.in_proj_ba",
"model.language_model.layers.2.linear_attn.in_proj_b",
"model.language_model.layers.2.linear_attn.in_proj_a",
"model.language_model.layers.2.linear_attn.in_proj_qkvz",
"model.language_model.layers.4.linear_attn.in_proj_ba",
"model.language_model.layers.4.linear_attn.in_proj_b",
"model.language_model.layers.4.linear_attn.in_proj_a",
"model.language_model.layers.4.linear_attn.in_proj_qkvz",
"model.language_model.layers.5.linear_attn.in_proj_ba",
"model.language_model.layers.5.linear_attn.in_proj_b",
"model.language_model.layers.5.linear_attn.in_proj_a",
"model.language_model.layers.5.linear_attn.in_proj_qkvz",
"model.language_model.layers.6.linear_attn.in_proj_ba",
"model.language_model.layers.6.linear_attn.in_proj_b",
"model.language_model.layers.6.linear_attn.in_proj_a",
"model.language_model.layers.6.linear_attn.in_proj_qkvz",
"model.language_model.layers.8.linear_attn.in_proj_ba",
"model.language_model.layers.8.linear_attn.in_proj_b",
"model.language_model.layers.8.linear_attn.in_proj_a",
"model.language_model.layers.8.linear_attn.in_proj_qkvz",
"model.language_model.layers.9.linear_attn.in_proj_ba",
"model.language_model.layers.9.linear_attn.in_proj_b",
"model.language_model.layers.9.linear_attn.in_proj_a",
"model.language_model.layers.9.linear_attn.in_proj_qkvz",
"model.language_model.layers.10.linear_attn.in_proj_ba",
"model.language_model.layers.10.linear_attn.in_proj_b",
"model.language_model.layers.10.linear_attn.in_proj_a",
"model.language_model.layers.10.linear_attn.in_proj_qkvz",
"model.language_model.layers.12.linear_attn.in_proj_ba",
"model.language_model.layers.12.linear_attn.in_proj_b",
"model.language_model.layers.12.linear_attn.in_proj_a",
"model.language_model.layers.12.linear_attn.in_proj_qkvz",
"model.language_model.layers.13.linear_attn.in_proj_ba",
"model.language_model.layers.13.linear_attn.in_proj_b",
"model.language_model.layers.13.linear_attn.in_proj_a",
"model.language_model.layers.13.linear_attn.in_proj_qkvz",
"model.language_model.layers.14.linear_attn.in_proj_ba",
"model.language_model.layers.14.linear_attn.in_proj_b",
"model.language_model.layers.14.linear_attn.in_proj_a",
"model.language_model.layers.14.linear_attn.in_proj_qkvz",
"model.language_model.layers.16.linear_attn.in_proj_ba",
"model.language_model.layers.16.linear_attn.in_proj_b",
"model.language_model.layers.16.linear_attn.in_proj_a",
"model.language_model.layers.16.linear_attn.in_proj_qkvz",
"model.language_model.layers.17.linear_attn.in_proj_ba",
"model.language_model.layers.17.linear_attn.in_proj_b",
"model.language_model.layers.17.linear_attn.in_proj_a",
"model.language_model.layers.17.linear_attn.in_proj_qkvz",
"model.language_model.layers.18.linear_attn.in_proj_ba",
"model.language_model.layers.18.linear_attn.in_proj_b",
"model.language_model.layers.18.linear_attn.in_proj_a",
"model.language_model.layers.18.linear_attn.in_proj_qkvz",
"model.language_model.layers.20.linear_attn.in_proj_ba",
"model.language_model.layers.20.linear_attn.in_proj_b",
"model.language_model.layers.20.linear_attn.in_proj_a",
"model.language_model.layers.20.linear_attn.in_proj_qkvz",
"model.language_model.layers.21.linear_attn.in_proj_ba",
"model.language_model.layers.21.linear_attn.in_proj_b",
"model.language_model.layers.21.linear_attn.in_proj_a",
"model.language_model.layers.21.linear_attn.in_proj_qkvz",
"model.language_model.layers.22.linear_attn.in_proj_ba",
"model.language_model.layers.22.linear_attn.in_proj_b",
"model.language_model.layers.22.linear_attn.in_proj_a",
"model.language_model.layers.22.linear_attn.in_proj_qkvz",
"model.language_model.layers.24.linear_attn.in_proj_ba",
"model.language_model.layers.24.linear_attn.in_proj_b",
"model.language_model.layers.24.linear_attn.in_proj_a",
"model.language_model.layers.24.linear_attn.in_proj_qkvz",
"model.language_model.layers.25.linear_attn.in_proj_ba",
"model.language_model.layers.25.linear_attn.in_proj_b",
"model.language_model.layers.25.linear_attn.in_proj_a",
"model.language_model.layers.25.linear_attn.in_proj_qkvz",
"model.language_model.layers.26.linear_attn.in_proj_ba",
"model.language_model.layers.26.linear_attn.in_proj_b",
"model.language_model.layers.26.linear_attn.in_proj_a",
"model.language_model.layers.26.linear_attn.in_proj_qkvz",
"model.language_model.layers.28.linear_attn.in_proj_ba",
"model.language_model.layers.28.linear_attn.in_proj_b",
"model.language_model.layers.28.linear_attn.in_proj_a",
"model.language_model.layers.28.linear_attn.in_proj_qkvz",
"model.language_model.layers.29.linear_attn.in_proj_ba",
"model.language_model.layers.29.linear_attn.in_proj_b",
"model.language_model.layers.29.linear_attn.in_proj_a",
"model.language_model.layers.29.linear_attn.in_proj_qkvz",
"model.language_model.layers.30.linear_attn.in_proj_ba",
"model.language_model.layers.30.linear_attn.in_proj_b",
"model.language_model.layers.30.linear_attn.in_proj_a",
"model.language_model.layers.30.linear_attn.in_proj_qkvz",
"model.language_model.layers.32.linear_attn.in_proj_ba",
"model.language_model.layers.32.linear_attn.in_proj_b",
"model.language_model.layers.32.linear_attn.in_proj_a",
"model.language_model.layers.32.linear_attn.in_proj_qkvz",
"model.language_model.layers.33.linear_attn.in_proj_ba",
"model.language_model.layers.33.linear_attn.in_proj_b",
"model.language_model.layers.33.linear_attn.in_proj_a",
"model.language_model.layers.33.linear_attn.in_proj_qkvz",
"model.language_model.layers.34.linear_attn.in_proj_ba",
"model.language_model.layers.34.linear_attn.in_proj_b",
"model.language_model.layers.34.linear_attn.in_proj_a",
"model.language_model.layers.34.linear_attn.in_proj_qkvz",
"model.language_model.layers.36.linear_attn.in_proj_ba",
"model.language_model.layers.36.linear_attn.in_proj_b",
"model.language_model.layers.36.linear_attn.in_proj_a",
"model.language_model.layers.36.linear_attn.in_proj_qkvz",
"model.language_model.layers.37.linear_attn.in_proj_ba",
"model.language_model.layers.37.linear_attn.in_proj_b",
"model.language_model.layers.37.linear_attn.in_proj_a",
"model.language_model.layers.37.linear_attn.in_proj_qkvz",
"model.language_model.layers.38.linear_attn.in_proj_ba",
"model.language_model.layers.38.linear_attn.in_proj_b",
"model.language_model.layers.38.linear_attn.in_proj_a",
"model.language_model.layers.38.linear_attn.in_proj_qkvz",
"model.language_model.layers.40.linear_attn.in_proj_ba",
"model.language_model.layers.40.linear_attn.in_proj_b",
"model.language_model.layers.40.linear_attn.in_proj_a",
"model.language_model.layers.40.linear_attn.in_proj_qkvz",
"model.language_model.layers.41.linear_attn.in_proj_ba",
"model.language_model.layers.41.linear_attn.in_proj_b",
"model.language_model.layers.41.linear_attn.in_proj_a",
"model.language_model.layers.41.linear_attn.in_proj_qkvz",
"model.language_model.layers.42.linear_attn.in_proj_ba",
"model.language_model.layers.42.linear_attn.in_proj_b",
"model.language_model.layers.42.linear_attn.in_proj_a",
"model.language_model.layers.42.linear_attn.in_proj_qkvz",
"model.language_model.layers.44.linear_attn.in_proj_ba",
"model.language_model.layers.44.linear_attn.in_proj_b",
"model.language_model.layers.44.linear_attn.in_proj_a",
"model.language_model.layers.44.linear_attn.in_proj_qkvz",
"model.language_model.layers.45.linear_attn.in_proj_ba",
"model.language_model.layers.45.linear_attn.in_proj_b",
"model.language_model.layers.45.linear_attn.in_proj_a",
"model.language_model.layers.45.linear_attn.in_proj_qkvz",
"model.language_model.layers.46.linear_attn.in_proj_ba",
"model.language_model.layers.46.linear_attn.in_proj_b",
"model.language_model.layers.46.linear_attn.in_proj_a",
"model.language_model.layers.46.linear_attn.in_proj_qkvz",
"model.language_model.layers.48.linear_attn.in_proj_ba",
"model.language_model.layers.48.linear_attn.in_proj_b",
"model.language_model.layers.48.linear_attn.in_proj_a",
"model.language_model.layers.48.linear_attn.in_proj_qkvz",
"model.language_model.layers.49.linear_attn.in_proj_ba",
"model.language_model.layers.49.linear_attn.in_proj_b",
"model.language_model.layers.49.linear_attn.in_proj_a",
"model.language_model.layers.49.linear_attn.in_proj_qkvz",
"model.language_model.layers.50.linear_attn.in_proj_ba",
"model.language_model.layers.50.linear_attn.in_proj_b",
"model.language_model.layers.50.linear_attn.in_proj_a",
"model.language_model.layers.50.linear_attn.in_proj_qkvz",
"model.language_model.layers.52.linear_attn.in_proj_ba",
"model.language_model.layers.52.linear_attn.in_proj_b",
"model.language_model.layers.52.linear_attn.in_proj_a",
"model.language_model.layers.52.linear_attn.in_proj_qkvz",
"model.language_model.layers.53.linear_attn.in_proj_ba",
"model.language_model.layers.53.linear_attn.in_proj_b",
"model.language_model.layers.53.linear_attn.in_proj_a",
"model.language_model.layers.53.linear_attn.in_proj_qkvz",
"model.language_model.layers.54.linear_attn.in_proj_ba",
"model.language_model.layers.54.linear_attn.in_proj_b",
"model.language_model.layers.54.linear_attn.in_proj_a",
"model.language_model.layers.54.linear_attn.in_proj_qkvz",
"model.language_model.layers.56.linear_attn.in_proj_ba",
"model.language_model.layers.56.linear_attn.in_proj_b",
"model.language_model.layers.56.linear_attn.in_proj_a",
"model.language_model.layers.56.linear_attn.in_proj_qkvz",
"model.language_model.layers.57.linear_attn.in_proj_ba",
"model.language_model.layers.57.linear_attn.in_proj_b",
"model.language_model.layers.57.linear_attn.in_proj_a",
"model.language_model.layers.57.linear_attn.in_proj_qkvz",
"model.language_model.layers.58.linear_attn.in_proj_ba",
"model.language_model.layers.58.linear_attn.in_proj_b",
"model.language_model.layers.58.linear_attn.in_proj_a",
"model.language_model.layers.58.linear_attn.in_proj_qkvz",
"model.language_model.layers.60.linear_attn.in_proj_ba",
"model.language_model.layers.60.linear_attn.in_proj_b",
"model.language_model.layers.60.linear_attn.in_proj_a",
"model.language_model.layers.60.linear_attn.in_proj_qkvz",
"model.language_model.layers.61.linear_attn.in_proj_ba",
"model.language_model.layers.61.linear_attn.in_proj_b",
"model.language_model.layers.61.linear_attn.in_proj_a",
"model.language_model.layers.61.linear_attn.in_proj_qkvz",
"model.language_model.layers.62.linear_attn.in_proj_ba",
"model.language_model.layers.62.linear_attn.in_proj_b",
"model.language_model.layers.62.linear_attn.in_proj_a",
"model.language_model.layers.62.linear_attn.in_proj_qkvz",
"mtp.fc",
"mtp.norm",
"mtp.pre_fc_norm_embedding",
"mtp.pre_fc_norm_hidden",
"mtp.layers.0.input_layernorm",
"mtp.layers.0.post_attention_layernorm",
"mtp.layers.0.self_attn.q_norm",
"mtp.layers.0.self_attn.k_norm",
"mtp.layers.0.mlp.gate",
"mtp.layers.0.mlp.shared_expert_gate"
],
"kv_cache_scheme": null,
"quant_method": "compressed-tensors",
"quantization_status": "compressed",
"sparsity_config": {},
"transform_config": {},
"version": "0.17.1"
},
"text_config": {
"attention_bias": false,
"attention_dropout": 0.0,
"attn_output_gate": true,
"bos_token_id": 248044,
"dtype": "bfloat16",
"eos_token_id": 248044,
"full_attention_interval": 4,
"head_dim": 256,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 17408,
"layer_types": [
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention",
"linear_attention",
"linear_attention",
"linear_attention",
"full_attention"
],
"linear_conv_kernel_dim": 4,
"linear_key_head_dim": 128,
"linear_num_key_heads": 16,
"linear_num_value_heads": 48,
"linear_value_head_dim": 128,
"mamba_ssm_dtype": "float32",
"max_position_embeddings": 262144,
"model_type": "qwen3_5_text",
"mtp_num_hidden_layers": 1,
"mtp_use_dedicated_embeddings": false,
"num_attention_heads": 24,
"num_hidden_layers": 64,
"num_key_value_heads": 4,
"output_gate_type": "swish",
"pad_token_id": null,
"partial_rotary_factor": 0.25,
"rms_norm_eps": 1e-06,
"rope_parameters": {
"mrope_interleaved": true,
"mrope_section": [
11,
11,
10
],
"partial_rotary_factor": 0.25,
"rope_theta": 10000000,
"rope_type": "default"
},
"tie_word_embeddings": false,
"use_cache": true,
"vocab_size": 248320
},
"tie_word_embeddings": false,
"transformers_version": "5.10.1",
"video_token_id": 248057,
"vision_config": {
"deepstack_visual_indexes": [],
"depth": 27,
"dtype": "bfloat16",
"hidden_act": "gelu_pytorch_tanh",
"hidden_size": 1152,
"in_channels": 3,
"initializer_range": 0.02,
"intermediate_size": 4304,
"model_type": "qwen3_5_vision",
"num_heads": 16,
"num_position_embeddings": 2304,
"out_hidden_size": 5120,
"patch_size": 16,
"spatial_merge_size": 2,
"temporal_patch_size": 2
},
"vision_end_token_id": 248054,
"vision_start_token_id": 248053
}

SRZhu26

12 days ago

Getting similar error with MTP on sglang, getting 0.0 acceptance

Adamiros

BottleCapAI org 12 days ago

Hi, we'll take a look into this, thanks for the report. We've confirmed MTP works on a single H200 in vLLM 0.24.0, but need some time to investigate these parallel setups.

oplatek

BottleCapAI org 11 days ago

Hi, we released a fix to the FP8 checkpoint which keeps the GDN linear-attention input projections (linear_attn.in_proj_a/b) in bf16 instead of FP8, which fixes the load crash on
Ampere/Ada GPUs. On Hopper it was working fine. It should also fix the MTP prediction issues.

MadGoatHaz

10 days ago

Yep, it loads (after pointing vllm towards the nvidia/cu13/lib/ dir)

oplatek changed discussion status to closed 9 days ago

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment