X · @teortaxesTex
· X / Twitter
RT vLLM: 🚀 @deepseek_ai's DSpark speculative decoding now runs natively in vLLM! What it is: a semi-autoregressive drafter that proposes several to…
RT vLLM🚀 @deepseek_ai's DSpark speculative decoding now runs natively in vLLM!What it is: a semi-autoregressive drafter that proposes several tokens in parallel with non-causal sliding-window attention, then verifies them in a single pass. Output stays identical, decoding takes fewer steps.How vLLM runs it: it reuses t