Files
DeepInfer/tests/engine
shunyadandClaude Opus 5.5 8898e97395 fix(sm120): refuse multi-host Engram groups right after rendezvous
Host-resident Engram tables are one /dev/shm mapping shared through
/proc/<pid>/fd, so every Engram group must sit on one host. The default
engram_parallel_size (0 = every rank) spans all nodes of a multi-node
deployment, which only failed on a bare assert in HostEngramBuffer after the
weights were loaded (and under python -O failed later with a misleading
"cannot open /proc/..." error).

- sm120_support.check_rank_placement (was check_distinct_devices) now also
  checks, from the hostnames it already gathers, that each Engram group
  (contiguous rank blocks) stays on one host, and names the offending ranks.
- HostEngramBuffer raises ValueError instead of asserting.
- README.sm120.md says multi-node deployments must set engram_parallel_size.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
2026-11-18 22:22:14 -08:00
..
2026-10-20 12:09:42 +08:00
2026-10-20 12:09:42 +08:00
2026-10-20 12:09:42 +08:00