Instructions to use RadixArk/Qwen3.8-27B-DSpark with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use RadixArk/Qwen3.8-27B-DSpark with Transformers:

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

pipe = pipeline("text-generation", model="RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True)

# Load model directly
from transformers import AutoTokenizer, AutoModel

tokenizer = AutoTokenizer.from_pretrained("RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True)
model = AutoModel.from_pretrained("RadixArk/Qwen3.8-27B-DSpark", trust_remote_code=True, device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use RadixArk/Qwen3.8-27B-DSpark with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "RadixArk/Qwen3.8-27B-DSpark"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/RadixArk/Qwen3.8-27B-DSpark

SGLang

How to use RadixArk/Qwen3.8-27B-DSpark 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 "RadixArk/Qwen3.8-27B-DSpark" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

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 "RadixArk/Qwen3.8-27B-DSpark" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "RadixArk/Qwen3.8-27B-DSpark",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use RadixArk/Qwen3.8-27B-DSpark with Docker Model Runner:
```
docker model run hf.co/RadixArk/Qwen3.8-27B-DSpark
```

Fix DSpark reference generation block width

by yisun0618 - opened 29 days ago

base: refs/heads/main

←

from: refs/pr/2

Discussion Files changed

+11

-5

Files changed (1) hide show

dflash.py +11 -5

dflash.py CHANGED Viewed

@@ -395,8 +395,9 @@ class DFlashDraftModel(Qwen3PreTrainedModel):
         max_length = num_input_tokens + max_new_tokens
         block_size = self.block_size
         output_ids = torch.full(
-            (1, max_length + block_size),
             self.mask_token_id,
             dtype=torch.long,
             device=target.device,
@@ -430,9 +431,14 @@ class DFlashDraftModel(Qwen3PreTrainedModel):
         acceptance_lengths = []
         start = input_ids.shape[1]
         while start < max_length:
-            block_output_ids = output_ids[:, start : start + block_size].clone()
-            block_position_ids = position_ids[:, start : start + block_size]
-            noise_embedding = target.model.embed_tokens(block_output_ids)
             draft_logits = target.lm_head(
                 self(
                     target_hidden=target_hidden,
@@ -443,7 +449,7 @@ class DFlashDraftModel(Qwen3PreTrainedModel):
                     past_key_values=past_key_values_draft,
                     use_cache=True,
                     is_causal=False,
-                )[:, -block_size + 1 :, :]
             )
             past_key_values_draft.crop(start)
             block_output_ids[:, 1:] = sample(draft_logits)

         max_length = num_input_tokens + max_new_tokens
         block_size = self.block_size
+        verify_width = block_size + 1
         output_ids = torch.full(
+            (1, max_length + verify_width),
             self.mask_token_id,
             dtype=torch.long,
             device=target.device,
         acceptance_lengths = []
         start = input_ids.shape[1]
         while start < max_length:
+            # The draft has ``block_size`` noise rows. Row j predicts the token at
+            # start+j+1, so target verification consumes the anchor plus all draft
+            # proposals (``block_size + 1`` tokens).
+            block_output_ids = output_ids[:, start : start + verify_width].clone()
+            block_position_ids = position_ids[:, start : start + verify_width]
+            noise_embedding = target.model.embed_tokens(
+                block_output_ids[:, :block_size]
+            )
             draft_logits = target.lm_head(
                 self(
                     target_hidden=target_hidden,
                     past_key_values=past_key_values_draft,
                     use_cache=True,
                     is_causal=False,
+                )[:, -block_size:, :]
             )
             past_key_values_draft.crop(start)
             block_output_ids[:, 1:] = sample(draft_logits)