Tag: sglang
All the articles with the tag "sglang".
-
Training a DFlash drafter on a B200 — the real grind behind block-diffusion speculative decoding
I trained a DFlash drafter for a 72B on 2×B200 with the latest SGLang: the version-drift tax, the warm-start trap, accept 1.49→1.71, and what's next.
-
I implement the papers, I don't just read them — a speculative-decoding field journal
How I actually learn new inference tech: build it. Training EAGLE3 and DFlash drafters for a 72B, the traps reading never warns you about, and DFlash v2.