…ias)

Eliminate the per-decode-round token D2H->H2D round-trip:
- sampler.py: emit the sampled token as int64 (was float32) so the decode
  method's int64 token output can be aliased directly as the next forward's
  int64 token input (value-preserving: argmax index; token ids < 2^24).
- main.cpp: read_token reads int64; each forward's on-device output token is
  aliased via make_tensor_ptr and fed straight back as the next step's token
  input (prefill->decode and decode->decode). Only the per-round position
  H2D remains.

Measured (int6/gguf, cuda graph OFF, p19/d128): post-load HtoD 261->132
(token H2D removed; ~= decode length); DtoH/DtoD counts unchanged (129),
bytes 4B->8B (token now int64). Greedy output byte-identical to prior export.

Kill the per-decode-round position H2D (the last per-round host->device copy
left after Option A): upload the full decode position array to device once
(single H2D), then each step copy that step's position from the array into the
fixed position input slot with an on-device D2D. Token stays aliased on device
(Option A). Per-round HtoD is now 0, independent of decode length; the fixed
input slot keeps it cuda-graph-safe (with cuda graph on, the D2D becomes a
captured cudaMemcpyAsync on the decode stream into the same slot).

Measured (int6/gguf, cuda graph OFF, p19/d128): post-load HtoD 132->5
(per-round H2D=0); DtoD 129->257 (+128 per-round pos d2d, the intended
H2D->d2d trade); DtoH unchanged (129). Greedy output byte-identical to prior
runs. Runner-only; reuses the int64-output export (no re-export).