vh/esh-pfi-infrastructure
1
0
Fork 0
Code Issues 7 Pull Requests Actions Packages Projects Releases Wiki Activity

docs(flash-next-seat): dealignai weights deleted — record that no local rollback exists

Browse Source 
Operator instruction: delete the displaced dealignai checkpoint. 125 GiB
reclaimed from /tank (59% -> 57% used). Verified before removing: not mounted
by any running or exited container, no symlinks, no inodes shared with the
converted orcarouter directory.

Every "rollback is two .env keys" statement across the stack README, the
.env.example, persistent-memory and its detail file was true when written and
is false now -- the .env backup still names paths that no longer exist.
Corrected in place rather than left as false reassurance, since a stale
rollback instruction is discovered precisely when it is needed.

Reverting this seat now costs a 126 GiB re-download. The quality A/B against
dealignai is likewise no longer runnable locally: its reference arm is gone.

The pristine 170 GiB orcarouter download is retained deliberately -- it is what
makes the PLE bf16->FP8 conversion reproducible without re-fetching -- and that
is now recorded so a future session does not reclaim it as an obvious duplicate.

Also notes that ~75 GiB of non-PLE shards are duplicated between the pristine
and converted orca directories (the convert's hardlinks hit EXDEV across two
container bind mounts); both now sit directly on /tank, so relinking would
reclaim it if /tank ever tightens.
This commit is contained in:
vh
2026-09-14 02:51:54 -07:00
parent 4390be947d
commit 1b5d6ba23a
4 changed files with 28 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files
persistent-memory.d/2026-09-14-fv-seat-reorg-and-orca-blocker.md
+8 -1
View File
@@ -101,7 +101,14 @@ cost decode speed, which was the standing risk of giving up FP4 tensor-core comp
- Quality A/B orca vs dealignai (the actual reason for the swap — the W4A4 long-context
degradation axis). Needs a controlled harness + noise floor.
- Deep-prefill probe at 262K against THIS checkpoint. Startup is not a depth test.
- Rollback is two `.env` keys; `.env.bak-preorca-20260914-023408` on the host.
- ⚠⚠ **NO LOCAL ROLLBACK.** dealignai weights DELETED 2026-09-14 on operator instruction
(125 GiB reclaimed). `.env.bak-preorca-20260914-023408` still names the old paths but they
no longer exist — it is a record, not a revert. Reverting = 126 GiB re-download.
The pristine 170 GiB `qwen38-flash-next-orcarouter-nvfp4` IS retained (redo the conversion
from it; do not delete it without a reason).
- Disk: ~75 GiB of non-PLE shards are duplicated between the pristine and converted orca dirs
(the convert's hardlinks hit EXDEV inside the container). Now that both sit directly on
/tank, relinking them would reclaim it — not urgent at 3.8T free.
- Disk: the convert **copied** ~75 GiB of unchanged shards because hardlinks hit `EXDEV`
(separate bind mounts of the same fs). Harmless; reclaimable by relinking if /tank tightens.