Block a user
Evaluate speculative decoding for neuron (EAGLE-3 first, bench-gated) — batch-1 decode latency
Sharper MoE caveat — why A3B (Qwen3.6-30B-A3B) is a separate, lower, uncertain bet
Refining the "MoE has a smaller win" note above with the actual mechanism, since A3B keeps coming up as a…
Evaluate speculative decoding for neuron (EAGLE-3 first, bench-gated) — batch-1 decode latency
/v1/models: re-expose
max_model_len (+ input/output) — Hermes Agent can't read context window from limit.context