Instructions to use lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound with Transformers:

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

pipe = pipeline("text-generation", model="lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound")

# Load model directly
from transformers import AutoModelForCausalLM
model = AutoModelForCausalLM.from_pretrained("lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound", device_map="auto")

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Use Docker

docker model run hf.co/lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound

SGLang

How to use lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound 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 "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound" \
    --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": "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound",
		"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 "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound" \
        --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": "lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound",
		"prompt": "Once upon a time,",
		"max_tokens": 512,
		"temperature": 0.5
	}'

Docker Model Runner
How to use lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound with Docker Model Runner:
```
docker model run hf.co/lvkaokao/DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound
```

DeepSeek-V4.1-Flash-MXFP4-Engram-AutoRound / README.md

lvkaokao

Upload folder using huggingface_hub

8e136b1 verified 6 days ago

preview code

Raw

History Blame Contribute Delete

3.17 kB

	---
	license: mit
	base_model: deepseek-ai/DeepSeek-V4.1-Flash
	library_name: transformers
	tags: [auto-round, mxfp4, engram, model-free, deepseek]
	---

	# DeepSeek-V4.1-Flash — D1 (Engram tables FP8→MXFP4), auto-round one-command

	Same artifact class as `DeepSeek-V4.1-Flash-D1-engram-mxfp4` (only the two engram
	embedding tables requantized FP8→MXFP4), but produced **end-to-end by a single
	auto-round `--model_free` command** (with the DeepSeek-V4.1 source-format patch set).

	Checkpoint size: 412.0 GB (vs 510.3 GB official, -19.3%). All 96,081 non-engram
	tensors verified byte-identical to the official checkpoint; engram tables are
	int8-packed E2M1 `[R,128]` + E8M0 `[R,8]` under their original names, rel_err ≈ 0.12
	vs the FP8 source (4-bit E2M1 theoretical band).

	## Quantization command

	```bash
	AR_MODEL_FREE_SHARD_PARALLELISM=1 \
	auto-round --model_name deepseek-ai/DeepSeek-V4.1-Flash \
	--model_free --scheme BF16 \
	--layer_config '{
	"engram.embed": {"bits": 4, "data_type": "mx_fp4", "group_size": 32},
	"indexer.wq_b": {"bits": 8, "data_type": "mx_fp8", "group_size": 32},
	"compressor": {"bits": 16},
	"indexer": {"bits": 16},
	"shared_experts": {"bits": 8, "data_type": "mx_fp8", "group_size": 32},
	"ffn.experts": {"bits": 4, "data_type": "mx_fp4", "group_size": 32},
	"attn": {"bits": 8, "data_type": "mx_fp8", "group_size": 32},
	"engram.wkv": {"bits": 8, "data_type": "mx_fp8", "group_size": 32},
	"main_proj": {"bits": 8, "data_type": "mx_fp8", "group_size": 32}}' \
	--output_dir <out>
	# afterwards: restore the official config.json (this repo's config.json is already official)
	```

	Notes on the recipe (learned the hard way):
	- `BF16` default keeps every unlisted family in full precision; FP8/MXFP4 source families
	listed with their same target format pass through byte-identically (no requant).
	- `layer_config` patterns are substring matches, first match wins: `ffn.experts` (not
	`experts`) must be used for routed experts so it cannot shadow `shared_experts`;
	`compressor`/`indexer` are BF16 and must be pinned to `bits:16` before `attn`.
	- `AR_MODEL_FREE_SHARD_PARALLELISM=1` is required for this model: parallel shard workers
	share one GPU and can OOM the giant-table (384M-row) quantization worker.

	## Inference (vLLM)

	Identical to `DeepSeek-V4.1-Flash-D1-engram-mxfp4`: vLLM `main` (≥ PR #56201) +
	`dsv41-quant-plugin` engram patch, official `config.json` (FP8 declaration) kept:

	```bash
	DSV41_ENGRAM_DTYPE=fp4 NCCL_NVLS_ENABLE=0 \
	vllm serve <this-model-dir> \
	--tensor-parallel-size 4 --max-model-len 8192 --language-model-only \
	--gpu-memory-utilization 0.90 --port 8100
	```

	## Provenance

	- auto-round: patched copy at main `@141e4c99` (+270 lines in
	`auto_round/utils/model_free_utils.py`: V4.1 source normalize/restore, blockwise FP8
	passthrough, chunked MXFP for giant tables, `should_skip` yields to explicit
	`layer_config`).
	- vLLM main nightly (`0.1.1.dev39+g46d2b23ac`).
	- Reference accuracy (same format, script-produced twin): gsm8k 92.19/92.27 vs 92.87
	baseline (n=1319, raw 5-shot, thinking off).