fix(checkpoint): FTW truncated shard raises OSError instead of silent garbage load - #25
Merged
jason-fxz merged 2 commits intoAug 24, 2026
Merged
Conversation
…ilent garbage load
|
Triaged while assembling a merged deployment branch for a 2× RTX 6000 Ada / 2× Xeon Gold 6526Y Linux box serving DeepSeek-V4-Flash with offloaded experts, to benchmark the open PRs together. FTW truncated-shard error handling. Not merged: this deployment serves HF safetensors directly and never exercises the FTW reader, so I would have been testing nothing. The change reads correctly — turning a bare OSError into a diagnosable message is the right instinct, and it is the same class of problem as the pin failure in #56. Flagging only so the absence of a report from me is not read as a problem found — I merged and benchmarked #30, #48, #56, #69, #70, #71 and #81, and left this one out deliberately. |
RuixiangMa
changed the title
Collaborator
|
ftw.py looks good! Just drop the tests and ready to merge. |
Contributor
Author
Done |
Collaborator
|
@RuixiangMa Great job! |
avlp12
pushed a commit
to avlp12/FreeToken
that referenced
this pull request
Aug 24, 2026
Brings in from FlashML-org/FreeToken main (5 commits since our merge base): bd372b6 fix(checkpoint): FTW truncated shard raises OSError instead of silent garbage load (FlashML-org#25) e0a3bbc Merge pull request FlashML-org#112 from FlashML-org/feat/split-residency 831d38a fix(moe): report the residency banks actually settle at eebb3f5 feat(moe): estimate expert-bank bytes from the model config c41833b feat(moe): per-layer host-bank residency -- split lock-CPU/pin-GPU layers, auto selection under capped pin quota 184a4f1 build(kernel-cache): add sm_80 (A100/A800) to default arches (FlashML-org#75) Conflicts (all in files where upstream's split-residency work and our own MoE/offload patches touched the same lines) were resolved to keep both intents, not to pick a side: * moe/host_banks.py: upstream's split-residency HostBank (backing="cuda" born-pinned option, LOCKED/PinPipeline/ResidencyPlan machinery) merged with our explicit 4096-byte alignment invariant (_off/_reg_len, aligned memoryview()/pin()). The alignment carve now applies to BOTH the mmap and the cuda backing, not just mmap. Also fixed a latent bug the combination would otherwise have introduced: HostBank.lock() mlock'd len(self._buf) (the over-allocated padded buffer) starting at the aligned self.addr, which overruns the mmap by up to one block; now mlocks self._reg_len like pin() already did. * moe/expert_banks.py: our bank-alignment startup diagnostic (_log_bank_alignment/_ALIGN) and upstream's parallel-reader support flag (_PARALLEL_READER_SUPPORTED) are independent additions next to each other -- kept both. In load_expert_banks, kept upstream's requested_residency()/_echo_residency() wrapping and added our _log_bank_alignment(banks) call right after the build, before echoing residency back to the caller. * models/deepseek_v4/moe.py: kept both prefill_routed guards -- our speculative-verify-wearing-a-prefill's-clothes check (route to _decode_routed under hybrid decode) runs first, then upstream's crossover-size-or-unpinned-layer check (route to super()._prefill_routed) -- both gate independently to their own fallback path. * moe/offload_cache.py: in copy_missing(), reordered so the unpinned (LOCKED) whole-layer pageable materialize check (upstream) runs before the --moe-copy-engine DMA doorbell dispatch (ours): an unpinned layer has no device alias, so it must never reach the doorbell path, which assumes a pinned bank layout. * engine/engine.py: took upstream's version of the cpu_layer_ids resolution -- it's a strict superset of ours (adds _auto_cpu_layers selection under a capped pin budget, which is the feature this sync exists to pull in); our `n_moe` local was just an unused-elsewhere alias, nothing of ours was lost. Also (per the task): rewrote sync-upstream.sh to `git merge` instead of `git rebase` -- uran-custom already carries its own merge commit (pr69/pr70/pr71), and rebasing across an existing merge commit invites history corruption. Verified in worktree /root/ft-sync (PYTHONPATH override, not the live editable install at /root/FreeToken): - python3 -m compileall python/freetoken: clean - import freetoken + the 7 touched modules: clean - /root/test_dma_doorbell.py (eager + graph phases): PASS - /root/test_bank_alignment.py: PASS - /root/test_moe_copy_engine_gate.py: PASS - /root/test_dma_dead_flag.py: PASS - ad hoc HostBank backing="cuda" (born-pinned) + lock() mlock-length fix smoke test: PASS Our uran-specific features (host_kv_tier.py, DmaCopyService + gating, alignment invariant, --moe-collect-stats, scheduler idle hooks) are unaffected outside the files above and behave identically. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Samfisheryu
pushed a commit
to Samfisheryu/FreeToken
that referenced
this pull request
Aug 26, 2026
… garbage load (FlashML-org#25) (cherry picked from commit bd372b6)
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Problem
_pread_into in ftw.py silently broke out of its read loop on EOF (os.preadv returning 0), leaving the destination buffer partially filled with uninitialized garbage. A truncated FTW shard file (from interrupted conversion, disk full, or corruption) would load partial weights with no error anywhere, producing silently corrupted model outputs.
Fix
cc @andy-yang-1 @jason-fxz