Red Hat AI(@RedHat_AI):We just shipped DFlash speculator checkpoints for Qwen3.5-397B-A17B. On math_reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~4.5 out of 7. Both checkpoints trained with the open source Speculators library from @vllm_project. Apache 2.0. Validated on NVIDIA H200. One flag to enable in vLLM: --speculative-config '{ "model": "RedHatAI/Qwen3.5-397B-A17B-speculator.dflash", "num_speculative_tokens": 7, "method": "dflash" }' Check it out:

2026.07.22 20:00

We just shipped DFlash speculator checkpoints for Qwen3.5-397B-A17B. On math_reasoning: ~5 out of 7 draft tokens accepted on average. On code (HumanEval): ~4.5 out of 7. Both checkpoints trained with the open source Speculators library from @vllm_project. Apache 2.0. Validated on NVIDIA H200. One flag to enable in vLLM: --speculative-config '{ "model": "RedHatAI/Qwen3.5-397B-A17B-speculator.dflash", "num_speculative_tokens": 7, "method": "dflash" }' Check it out: