RedHatAI/GLM-5.2-speculator.dspark
91.8k
RedHatAI/GLM-5.2-speculator.dspark
This is a preliminary (and subject to change) DSpark speculator model for RedHatAI/GLM-5.2-NVFP4-FP8.
It was trained using the Speculators library on the mgoin/open-perfectblend-glm5.2-regen dataset.
Note:
It was validated on Nvidia B200, other hardware validation pending.
Training Details
Launch training
scripts/train.py \
--verifier-name-or-path RedHatAI/GLM-5.2-NVFP4-FP8 \
--data-path ./output/dspark_glm52 \
--vllm-endpoint http://localhost:8000/v1 \
--save-path ./output/dspark_glm52/checkpoints \
--epochs 1 \
--lr 3e-4 \
--total-seq-len 8192 \
--speculator-type dspark \
--block-size 8 \
--max-anchors 1024 \
--num-layers 3 \
--target-layer-ids 2 20 39 58 75 \
--markov-rank 256 \
--markov-head-type vanilla \
--enable-confidence-head \
--confidence-head-with-markov \
--loss-fn '{"ce": 0.1, "tv": 0.9}' \
--confidence-head-alpha 1.0 \
--fsdp-shard \
--logger tensorboard \
--log-dir ./output/dspark_glm52/logs \
--on-missing generate \
--on-generate delete \
--checkpoint-freq 0.01 \
--request-timeout 60 \
--max-retries 2Deployment
Deploy with vLLM using the speculator as a draft model.
vllm serve RedHatAI/GLM-5.2-NVFP4-FP8 \
--max-model-len 20480 \
--spec-model RedHatAI/GLM-5.2-speculator.dspark \
--spec-method dspark \
--spec-tokens 7 \
-tp 8Preliminary Evaluations
Per-Position Acceptance Rate
