Instructions to use tiny-random/deepseek-v4.1-flash with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use tiny-random/deepseek-v4.1-flash with Transformers:

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

pipe = pipeline("text-generation", model="tiny-random/deepseek-v4.1-flash")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# pip install -U transformers accelerate
# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("tiny-random/deepseek-v4.1-flash", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use tiny-random/deepseek-v4.1-flash with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "tiny-random/deepseek-v4.1-flash"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "tiny-random/deepseek-v4.1-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/tiny-random/deepseek-v4.1-flash

SGLang

How to use tiny-random/deepseek-v4.1-flash 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 "tiny-random/deepseek-v4.1-flash" \
    --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": "tiny-random/deepseek-v4.1-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

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 "tiny-random/deepseek-v4.1-flash" \
        --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": "tiny-random/deepseek-v4.1-flash",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use tiny-random/deepseek-v4.1-flash with Docker Model Runner:
```
docker model run hf.co/tiny-random/deepseek-v4.1-flash
```

yujiepan commited on 8 days ago

Commit

d83ea6c

verified ·

1 Parent(s): e2fb17b

Simplify model card

Browse files

Files changed (1) hide show

README.md +6 -14

README.md CHANGED Viewed

@@ -48,19 +48,9 @@ Note:
     expert counts, vocabulary rows, and 32-wide quantization blocks divide cleanly by 2.
     The online example enables the embedded three-stage DSpark/MTP draft explicitly.
-  - Validated on two NVIDIA H20 GPUs with Python 3.12.13, CUDA Toolkit 13.0,
-    torch 2.14.1, SGLang `0.5.23.dev384+g9ab74b851`, FlashInfer 0.7.2,
-    Transformers 5.19.0, TileLang 0.1.12, and safetensors 0.8.0. Separate offline
-    `sglang.Engine` runs using the same TP=2/backend settings reached engine-ready
-    with both base decoding and `speculative_algorithm="DSPARK"`; CUDA Graph remained
-    enabled, and the latter reported DSpark enabled, generated all three cases
-    (including `Hello` with exactly 10 new tokens), and shut down with exit code 0.
-    This artifact is byte-identical to the
-    separately generated 1017 tiny variant used for that runtime test (SHA-256
-    `53aae999fdcacd310c400a2fc3112bb68ce35588441784c75dca5820abf0f35b`). The README
-    keeps the equivalent online `sglang serve` form for normal deployment. The
-    official source `inference/convert.py` also produced two shards which loaded
-    strictly into the source runtime for both ranks.
 | File path | Size |
 |------|------|
@@ -592,4 +582,6 @@ main()
 ### Change log:
 - 2026-09-10: Initial version.
-- 2026-10-20: Replace the handwritten tensor schema with the pinned official V4.1 inference implementation, align all TP=2/DSV4 dimensions, preserve the three-stage DSpark/MTP draft, add the SGLang TP=2 + DSpark launch profile, and document source-versus-tiny structure and validated runtime versions.

     expert counts, vocabulary rows, and 32-wide quantization blocks divide cleanly by 2.
     The online example enables the embedded three-stage DSpark/MTP draft explicitly.
+  - TP=2 with DSpark/MTP and CUDA Graph was validated on two NVIDIA H20 GPUs using
+    Python 3.12.13, CUDA 13.0, torch 2.14.1, SGLang
+    `0.5.23.dev384+g9ab74b851`, FlashInfer 0.7.2, and Transformers 5.19.0.
 | File path | Size |
 |------|------|
 ### Change log:
 - 2026-09-10: Initial version.
+- 2026-10-20: Added an official-runtime-derived tiny checkpoint with TP=2 and DSpark/MTP support.
+This repo is generated by GPT-5.6-Sol.