Niko1221 9253c92ad7 The PCIe share by the copy kernel for every pack (#31, #29); setup and profile fixes (#46, #49, #45) ...

- --pcie-mode auto is the copy kernel for native packs too. Issue #31's thread
  dumps show the host stuck for good in the DMA path's cudaMemcpyAsync (a driver
  lock) inside a verify window while the GPU spins on the flag those copies
  raise. The copy kernel needs no host CUDA call there; IQ3_S decode 45.3 -> 44.8
  tok/s. --pcie-mode dma keeps the old path.
- setup: a locally compiled engine records its version; one kept after a failed
  compile is recognised by the version in its binary, and a config it cannot
  read (--prefill auto on 0.1.12) goes back to 2048 (#49).
- setup: nvcc in /opt/cuda (Arch), a clearer message off Ubuntu/Debian (#46);
  a failed build is tried once more (#45: ptxas's intermittent PTX parse error).
- data/expert-profile.bin ranks all 24,576 experts (the first 8,000 unchanged):
  the cache stopped at 8,000 slots on 24-32 GB cards (#46). tools/make_profile.py
  builds or extends a profile from --dump-routing traces; --expert-cache 0 with a
  profile now means auto.

2026-09-28 11:02:44 +02:00

192 KiB

Raw Permalink History

View Raw