Block a user
neuron: emit usage (prompt/completion tokens) on SSE streams
[epic] Multi-tenant governance: auth, federated token budgeting, concurrency control
fix(ci): drop the unused flash-attn feature from neuron builds (#42)
ci: Build neuron-ampere intermittently fails — ptxas segfault in candle-flash-attn sm_86 kernels
fix(ci): drop the unused flash-attn feature from neuron builds (#42)
feat(neuron): speculative decoding — acceptance core + config (#25, phase 1)
feat(neuron): speculative decoding — acceptance core + config (#25, phase 1)