inkling: adopt route_trace.h, keeping the IKU1 history readable - #742
Merged
Merged
Conversation
Third engine onto the shared telemetry from JustVugg#700, after colibri.c (JustVugg#716) and kimi_k3.c (JustVugg#719). The counters, the load and the save move to route_trace.h; the bump sites are untouched, since m->eusage now aliases rt_counts_all(). The transition is the point: rt_load reads both the IKU1 block every previous inkling wrote and the shared text format, so an existing .coli_usage keeps working and is rewritten in the new form. The header checks the old pins_load did inline -- magic, n_layers, n_experts against the live config -- all still fire, now in the reader, which additionally refuses a history written by a different engine. Narrower than before, never wider; and parse geometry does not bend to a trusted path the way identity does. Fixes a latent bug on the way: pins_load documents PIN_N=0 as "seeds the ranking from the history but pins nothing", but the npin guard ran before the memcpy, so the counters started at zero and the next usage_save replaced the accumulated ranking with that run's counts alone. Verified on the tiny fixture: rebuild clean, oracle token-exact (36/36 teacher-forced, 24/24 generated), make check 273 passed / 34 skipped, and the built engine reading a planted legacy history pins the right 9 experts while dropping the dense layer's counts. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
terrizoaguimor
added a commit
to terrizoaguimor/colibri
that referenced
this pull request
Aug 1, 2026
Fourth and final engine for JustVugg#700, after colibri.c (JustVugg#716), kimi_k3.c (JustVugg#719) and inkling.c (JustVugg#742). Every engine that routes experts now writes the same format. m->freq moves from one flat [n_layers * n_experts] block to route_trace.h's row per layer, so the three read sites -- the hot-pin ranking, the bump in moe() and the LFRU eviction guard -- change shape but not meaning. last_access stays flat; it is a separate array route_trace.h does not own. Every olmoe layer routes and there is no MTP layer, so the only row dropped is the spare one rt_init leaves. The history is opt-in behind COLI_USAGE, exactly as kimi_k3 does it: with the variable unset nothing is loaded and nothing is written, so the default path is unchanged. PPL=1 deliberately does not save, so a loss sweep cannot fold its own tokens into the persisted ranking. Verified against the real OLMoE-1B-7B-0125-Instruct converted with tools/convert_olmoe_merged.py. Output is byte-identical to dev on the same run, down to hit=1216 miss=832 -- the eviction path decides exactly as before, which is the property the layout change could have broken. The COLI_USAGE round trip writes the -1/-2 header with the olmoe identity, leaves no row for the dropped layer, and accumulates 2048 -> 4096 across two runs. make check green. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
terrizoaguimor
added a commit
to terrizoaguimor/colibri
that referenced
this pull request
Aug 1, 2026
Fourth and final engine for JustVugg#700, after colibri.c (JustVugg#716), kimi_k3.c (JustVugg#719) and inkling.c (JustVugg#742). Every engine that routes experts now writes the same format. m->freq moves from one flat [n_layers * n_experts] block to route_trace.h's row per layer, so the three read sites -- the hot-pin ranking, the bump in moe() and the LFRU eviction guard -- change shape but not meaning. last_access stays flat; it is a separate array route_trace.h does not own. Every olmoe layer routes and there is no MTP layer, so the only row dropped is the spare one rt_init leaves. The history is opt-in behind COLI_USAGE, exactly as kimi_k3 does it: with the variable unset nothing is loaded and nothing is written, so the default path is unchanged. PPL=1 deliberately does not save, so a loss sweep cannot fold its own tokens into the persisted ranking. Verified against the real OLMoE-1B-7B-0125-Instruct converted with tools/convert_olmoe_merged.py. Output is byte-identical to dev on the same run, down to hit=1216 miss=832 -- the eviction path decides exactly as before, which is the property the layout change could have broken. The COLI_USAGE round trip writes the -1/-2 header with the olmoe identity, leaves no row for the dropped layer, and accumulates 2048 -> 4096 across two runs. make check green. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
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
2 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.
Third engine onto the shared telemetry from #700, after
colibri.c(#716) andkimi_k3.c(#719). The counters, the load and the save move to
route_trace.h; the bump sites areuntouched, because
m->eusagenow aliasesrt_counts_all().The transition is the point.
rt_loadreads both theIKU1block every previous inklingwrote and the shared text format, so an existing
.coli_usagekeeps working and is rewrittenin the new form. The magic /
n_layers/n_expertscheckspins_loaddid inline all stillfire, now in the reader, and for an
IKU1block the acceptance is unchanged. The reader addsthe other direction — a non-inkling engine cannot read an
IKU1file — which was previouslyfree, because only inkling had the code path. Dimension mismatches are refused at any trust
level, since there the dimensions are the parse geometry rather than an attribution.
It also fixes a latent bug.
PIN_N=0is documented as seeding the ranking from the historywithout pinning, but the
npinguard ran before thememcpy, so it seeded nothing and thenext
usage_savereplaced the accumulated ranking with that run's counts alone.Verified on the tiny fixture: clean rebuild, oracle token-exact (36/36 teacher-forced argmax,
24/24 generated),
make check273 passed / 34 skipped, and the built engine reading a plantedlegacy history pins the right 9 experts while dropping the dense layer's counts. Detail and
the dimension-refusal cases are in #700.
🤖 Generated with Claude Code