No official torrent yet — requesting it tells the flock what to host next. You cannot seed a catalog-only page.
Cataloged from RedHatAI/Qwen3.8-27B-speculator.dspark
All models by RedHatAI →DSparkDraftModel
Qwen3_5ForConditionalGenerationThis is a DSpark speculator model for Qwen3.8-27B. It was trained using the Speculators library (version 0.8.0.dev221).
DSpark extends DFlash with a Markov head for modeling intra-block token dependencies and a confidence head for predicting per-position acceptance. The 5-layer draft model consumes auxiliary hidden states from layers 4, 12, 20, 28, 36, 44, 52, and 60 of the target model and proposes up to 8 tokens per decoding step.
This checkpoint was warm-started from an earlier Qwen3.8-27B DSpark checkpoint and trained on a Qwen3.8-27B-regenerated version of Open PerfectBlend. Data preparation produced 1,739,710 8,192-token training examples with a 99/1 train-validation split. Hidden-state extraction used four independent vLLM data-parallel replicas, while four FSDP ranks trained the draft model.
The released checkpoint is from global step 107,520, or approximately 75% of the planned one-epoch run. It used the full verifier vocabulary, sample_from_anchor=true, and up to 1,024 anchors per sequence.
Hidden-state extraction used vLLM 0.29.0 with data-parallel size 4, tensor-parallel size 1, and target layer IDs 4 12 20 28 36 44 52 60. Training used Speculators commit 876e2b6.
Evaluation used vLLM 0.29.0, a dense Qwen/Qwen3.8-27B verifier.
Per-position acceptance rates:
Evaluation of RedHatAI/Qwen3.8-27B-speculator.dspark using 8 speculative tokens on MRCR 8-Needle.
Across HumanEval, math reasoning, and RAG, DSpark consistently delivers higher throughput and better interactivity than MTP with the same eight speculative tokens. The advantage is strongest at low-to-medium concurrency—particularly for math reasoning—and remains positive at concurrency 128, though it narrows for RAG. Both methods scale smoothly, while DSpark sustains lower per-token latency as load increases.
train: speculator_type: dspark seed: 42 verifier: verifier_name_or_path: Qwen/Qwen3.8-27B data: total_seq_len: 8192 train_data_ratio: 0.99 max_anchors: 1024 loss: loss_fn: '{"ce":0.1,"tv":0.9}' optimizer: optimizer: muon lr: 0.001 muon_lr: 0.001 trainer: epochs: 1 checkpoint_freq: 0.05 fsdp_shard: true dflash: block_size: 8 sample_from_anchor: truevllm serve Qwen/Qwen3.8-27B \ --speculative-config '{"model":"RedHatAI/Qwen3.8-27B-speculator.dspark","num_speculative_tokens":8,"method":"dspark"}'