No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from RedHatAI/Qwen3-8B-speculator.dflash
All models by RedHatAI →This is a DFlash speculator model for Qwen/Qwen3-8B.
This model was trained using the Speculators library on a subset of Magpie-Align/Magpie-Llama-3.1-Pro-300K-Filtered and the train_sft split of HuggingFaceH4/ultrachat_200k. Responses were regenerated by Qwen3-8B (with reasoning). Training compute for this model was sponsored by Modal.
Using the Speculators library and the helper scripts provided in the repo.
Must be run once vLLM has finished launching and is running in the background.
Per-position token acceptance rates across datasets:
(with reasoning enabled)
Paper: DFlash: Block Diffusion for Flash Speculative Decoding
# In virtual environment with speculators installedpython scripts/prepare_data.py \ --model Qwen/Qwen3-8B --data ./regenerated_data.jsonl \ --output ./output \ --seq-length 8192# In (separate) virutal environment with vllm installedCUDA_VISIBLE_DEVICES=0,1 vllm_venv/bin/python scripts/launch_vllm.py \ Qwen/Qwen3-8B \ --target-layer-ids 2 10 18 26 34 \ -- --port 8000 \ --gpu-memory-utilization 0.9 \ --disable-uvicorn-access-log \ --tensor-parallel-size 1 \ --data-parallel-size 2# In virtual environment with speculators installedCUDA_VISIBLE_DEVICES=2,3 torchrun \ --standalone \ --nproc_per_node 2 \ scripts/train.py \ --verifier-name-or-path Qwen/Qwen3-8B \ --speculator-type dflash \ --num-layers 5 \ --data-path ./output \ --vllm-endpoint http://localhost:8000/v1 \ --save-path ./output/checkpoints \ --epochs 3 \ --lr 0.0006 \ --total-seq-len 8192 \ --on-missing generate \ --on-generate delete \ --seed 42 \ --log-freq 100 \ --draft-vocab-size 32000 \ --draft-arch qwen3 \ --target-layer-ids 2 10 18 26 34 \ --draft-hidden-act silu \ --scheduler-type cosine \ --max-anchors 3072 \ --prefetch-factor 2 \ --num-workers 8# Install vLLM from the required PRpip install git+https://github.com/vllm-project/vllm.git@refs/pull/41880/head # Deploy with speculative decoding vllm serve Qwen/Qwen3-8B \ --tensor-parallel-size 1 \ --max-model-len 16384 \ --speculative-config '{ "model": "RedHatAI/Qwen3-8B-speculator.dflash", "num_speculative_tokens": 7, "method": "dflash" }'