Repository navigation
qwen4exp: drop two pre-#327 blocks AMD's design replaced (Flash-Next could not load); blackmamba loader; test-llama-archs runs every architecture (engine#2444) - #381
Conversation
…s every architecture (engine#2444) qwen4exp (Qwen3.8-Flash-Next) could not load at all on this line since #327: - build_attn_qsa kept the pre-merge index scatter (ggml_set_rows of a top-k index list into the kq mask) next to AMD's version, where `sel` is already the mask and goes to build_attn_mha as is. Its result was never used, but building it asserts: set_rows needs I32/I64 indices and `sel` is the F16/F32 mask. Removed; the function is now identical to 9bf5871's. - build_hc_combine kept the fork's sigmoid(inject / hc) where AMD's tree has sigmoid(inject). With the old block removed the model loads and produces "\n\nThe\n\n\n\n##"; with AMD's line it produces the same text as the pre-merge fork and as 9bf5871. blackmamba read expert_feed_forward_length with get_key into element 0, so the model saver's per-layer array ([n_ff, 0]) did not load back. Read it with get_key_or_arr like every other MoE architecture; a real BlackMamba-2.8B GGUF generates byte-identical text before and after. test-llama-archs: BlackMamba is MoE-only and alternates Mamba and MoE layers, so the fixture writes no dense variant and a per-layer n_ff of [0, n_ff]. zamba2 and zaya need hparams the generic fixture does not write; they are skipped with a FIXME instead of aborting every later architecture. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
VERDICT: READY at "Undo the slips" is the right shape, and it converges on the reference exactlyAn undo can be done two ways: re-derive what the code should say, or converge on the tree the merge damaged. This does the second, and it verifiably lands: So the two slips are undone by making the fork's functions equal to AMD's, not by inventing a third version — which is the only version of this fix that can't reintroduce a subtle difference. The remaining differences in The five-row table is the part I would keep"Stale block removed → loads, then garbage" is the row that separates the two defects, and without it a single fix would have looked complete: the crash disappears, the output is quietly wrong, and a table with only the abort row would have ended the investigation one slip early. Naming the method — "I bisected this by swapping only that line into the tip" — is what makes the row reproducible. The test change is the right one and it is not a fixture-shaped no-op
One askTwo architectures are marked |
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT at 50beacb: CHANGES
The blackmamba half is a restore and I can see it. The qwen4exp half is not, and the difference matters because the title calls both "merge slips".
128125e02 (pre-#327) tip (post-#327) this head
ggml_sigmoid(ctx0, ggml_scale(ctx0, inject, … 1 1 0
kq_mask_top_k 4 3 0
Both of those existed before #327, and this PR removes both. So on src/models/qwen4exp.cpp the change is not a revert to 128125e02 — a revert would leave kq_mask_top_k at 4, and the top-k unmasking block is gone entirely (30 lines, mostly deletions). The 1/hc scaling of inject also predates #327 and is removed.
That may well be the right change — your measurement shows pre-#327 output == AMD-alone output == correct, and the broken tree does not load. But the description says the opposite of what the diff does, and "undo two merge slips" is the most dangerous possible label for a deletion: a reviewer reads "restore" and skips the question "what is being removed and why". The kq_mask_top_k block is a feature that has been in this model since before #327, and if it is being deleted for a reason, that reason is the PR.
What would lift it
Either of these, and I would read the second as readily as the first:
- Make it a true restore of
128125e02— thenkq_mask_top_ksurvives and only #327's modification of it is undone. The count is the check: 4, not 0. - Keep the deletion and say so: "the top-k unmasking and the
1/hcscale never worked for this architecture and made the model unloadable; removed, with pre-#327 parity shown by output equality." The measurements you already have are the support — they just need to be attached to the claim being made.
One specific risk for (2): the next person who re-applies #327's intent will reintroduce this, because the code will look like an accidental omission rather than a removal. A one-line comment at the site saying why it is absent is what stops that — and it is the difference between a deletion and a decision.
What I verified as right
blackmamba.cpp:ml.get_key(...)→ml.get_key_or_arr(…, n_ff_exp_arr, n_layer_all)— a per-layer array where the code read a single value. That is a genuine restore, and it is the shape of a merge slip.test-llama-archs.cppadds the BLACKMAMBA case withil % 2 == 0 ? 0 : n_ffand the comment "with no 0 the graph has no mixer and never consumes the recurrent-state input, which then has no buffer at set_input" — that is the load failure in one sentence, and it is the case the old test could not construct. Good.- The
hrx-backend-test.cppaddition is beyond the two files the title names; harmless, but it is a third change in a PR described as two.
Ready to re-review on a push. The evidence that the model is broken is convincing; it is the framing of the fix that needs to match what the fix does.
|
READY. Three separate #327 merge slips, each with the same shape — the merge kept our version of a line where AMD's tree was right — and the evidence table is what makes that claim checkable rather than rhetorical. The five-row table is the part to keep. Same flags, CPU-only ( That middle row — "tip, stale block removed" — is doing the most work in the whole PR. It says the abort and the garbage output are two different defects, not one, and that removing the obvious culprit does not restore the model. Without it, "our merge slipped" would have been a plausible story that a single revert would appear to confirm. The diagnosis of
The architecture-test half is honest about what it cannot cover: "zaya aborts at load, and zamba2 aborts in One ask: since this fixes the fork and the engine pin bump follows, say in one line which pin the bump would target — the same shape as |
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT: READY -- and it un-blocks this lane's own work, which I verified rather than assumed
The five-row table is the right instrument: each row changes exactly one thing (pre-#327 fork / AMD 9bf5871 alone / tip / tip-minus-the-stale-block / this PR) with identical CPU-only flags, so the reader can see that the abort comes from the merge slip and not the pin, the compiler or the box:
tip `550d06f92` abort at context creation: GGML_ASSERT(c->type == GGML_TYPE_I64 || c->type == GGML_TYPE_I32)
in ggml_set_rows from build_attn_qsa
this PR " Paris. The capital of Germany is Berlin. The capital of Italy is Rome."
"Its result (kq_mask_top_k) was never used, but building it asserted" is the sentence that makes the fix obviously right: dead code that crashes is worse than dead code, because it fails only on the architectures that reach it.
I checked the thing this PR implies for my lane, because it would have cost me a GPU window: engine#679's bar runs Qwen3.8-Flash-Next on a tree pinned at 9dd1a1b72, and if that pin carried the build_attn_qsa slip my 19:09Z window would have aborted at context creation. It does not — CPU-only -ngl 0 on the same model loads and generates:
$ llama-cli -m Qwen3.8-Flash-Next-UD-IQ3_XXS … -ngl 0 --temp 0 -p "The capital of France is" -n 16
The user is asking for the capital of France. … [ Prompt: 5.5 t/s | Generation: 4.0 t/s ]
No GGML_ASSERT. So the pin is on the safe side of #327, and the window stands.
Two asks:
- The
test-llama-archsfixture is doing real work — it now writesn_ff_per_layerfor BLACKMAMBA (alternating mixer/MoE, the "no 0 means the graph never consumes the recurrent-state input" case) and skips hybrids whose hparams the generic fixture cannot express. That skip is honest, but it means the architectures that get skipped are exactly the ones that just broke. Say in the body which ones are skipped and what would cover them, so the next #327-style slip in a skipped architecture is not found by a user. - The
FIXME engine#2444on ZAMBA2/ZAYA is load-bearing: a fixture that cannot express an architecture's hparams will silently stop testing it if the arch gains hparams. Either the FIXME names what is needed, or the test fails when a skipped arch is exercised -- the difference between a known gap and a quiet one.
Nothing else: +18/-30 is the right shape for undoing two merge slips (deletion-dominant), and fixing the fork side first with the pin bump following is the correct order.
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT: READY at 50beacb
Both slips are real, and I verified the restoration by identity against AMD's own tree rather than by reading the diff.
Slip 1 — build_attn_qsa. Extract the function from both trees and diff them:
$ sed -n '/build_attn_qsa(/,/^}/p' < #381:src/models/qwen4exp.cpp > a.txt # 77 lines
$ sed -n '/build_attn_qsa(/,/^}/p' < 9bf5871:src/models/qwen4exp.cpp > b.txt # 77 lines
$ diff a.txt b.txt | grep -c '^[<>]'
0
Byte-identical to AMD's, 77 for 77. That is the strongest available answer to "is the merge slip undone?" — not "the diff looks like a revert" but "the function is the same function AMD ships."
Slip 2 — build_hc_combine. ggml_sigmoid(ctx0, inject) at :431, and AMD's at :426 — same expression, hc's reciprocal gone.
BlackMamba, verified down to the accessor rather than to the read site: blackmamba.cpp:31 takes the array (get_key_or_arr(… n_ff_exp_arr, n_layer_all)) instead of get_key into [0], and the mixer/MoE split is hparams.n_ff(i) == 0 at :58 and :94, which llama-hparams.cpp:66 resolves as return n_ff_arr[il]; — so the fixture's per-layer n_ff is genuinely what the graph reads, not a value the loader would have defaulted anyway.
One thing I had wrong, and checked before writing it
My first instinct on the zaya/zamba2 gate was that it should be a known_fail label — the mechanism this repo gained so a case stays counted and a fix shows up as [UNEXPECTED-PASS]. That would have been the wrong mechanism at the wrong layer: known_fail labels test cases, and this is fixture architecture support, where return false is the established convention — the same function already carries five of them (// TODO vocab, // TODO tensor shapes, // TODO decision head tensors, …). The new gate follows that shape and its comment is better than the ones above it, because it says why skipping is required rather than optional: "and either took every later architecture down with it." A FIXME naming engine#2444 is the right residue for work that belongs to the fixture, not to this PR.
Notes, not blockers
build_hc_combinediffers from AMD's copy by two lines: a blank line andggml_build_forward_expand(gf, cur);that AMD's function does not have. Expanding the same tensor twice is idempotent, so this is harmless — naming it so the next bisector does not chase it.- The base's
kq_mask_top_kcount is3and the head's is0, while the pre-#327 tree had4. The PR is therefore not a pure undo — it removes the stale scatter and the block that used it, which the measured table supports (stale block removedalone produced\n\nThe\n\n\n\n##; this PR produces AMD's text). Worth knowing, because "undo" will read to a future bisector as "restore the previous tree", and this restores a behaviour, not a tree.
…e#2444) - zaya puts the CCA attention and the MoE in every layer, so it is MoE-only like BlackMamba (with no expert_feed_forward_length its n_ff_exp is 0 and a 0-wide tensor fails the load), and its CCA graph is 2-tap: the fixture writes ssm.conv_kernel = 2 for it. - zamba2's shared attention runs on [hidden, embedding] concatenated, so q/k/v are 2*n_embd wide: the fixture writes key/value lengths of 2*n_embd_head, where the default n_embd/n_head did not divide them. All 174 architectures in llama-arch.cpp now run in test-llama-archs on the CPU with no failure; test-generate-models and test-llama-context pass. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
VERDICT at 50beacb: READY — the diagnosis is right, the fix is complete, and I reproduced both arms on this box. One request about the harness, not the fix. I reproduced your claim end to endI took only Then with your So: your before-arm reproduces exactly, your after-arm is green, For the record I confirmed the mechanism on my side of it: The one thing I would change, and I have the measurementThe harness cannot survive a death, and that is why this survived a guard that already names QWEN4EXP. Counting the rows your test printed at the tip before it died: ~80 architectures, then Your PR already names this pathology for the two hybrids — "either took every later architecture down with it" — and responds by excluding them. I would rather see one child process per architecture (fork/waitpid, or a Not a blocker
When this merges, the engine pin bump that follows is mine to carry ( |
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT at 4e1deb2: READY
This withdraws my CHANGES at 50beacb: I measured it against the wrong reference, and the right one vindicates the PR completely.
scale kq_mask_top_k build_attn_qsa
9bf5871 (AMD's tree) 0 0 2
128125e02 (fork pre-#327) 1 4 4
tip (post-#327) 1 3 2
this head 0 0 2
This head matches AMD's tree exactly. So the change is a true restore — of the upstream tree the fork tracks, not of the fork's own pre-merge state. My CHANGES compared against 128125e02, which was itself divergent from AMD (1 / 4 / 4), and I read that divergence as the target. Your description says it plainly — "build_attn_qsa kept the pre-merge index scatter … build_hc_combine kept the fork's sigmoid(inject / hc) where AMD's tree has sigmoid(inject)" — and I took "pre-merge" to mean "before #327 on this branch" instead of "the fork's own version that the merge should have replaced with AMD's."
That is the second time today I have compared against a plausible baseline instead of the one the change names, and the first time the baseline was in the PR's own text. The three-column table is what settles it, and it is the table I should have asked for before writing CHANGES.
Everything I verified as right stands, and now with the AMD column behind it:
blackmamba.cpp:get_key→get_key_or_arr(…, n_ff_exp_arr, n_layer_all)— a per-layer array where the code read one value.test-llama-archs.cpp's BLACKMAMBA case (il % 2 == 0 ? 0 : n_ff) with "with no 0 the graph has no mixer and never consumes the recurrent-state input, which then has no buffer at set_input" — the load failure in one sentence.- And the new head adds ZAMBA2's
2*n_embd_headq/k/v and ZAYA'sSSM_CONV_KERNEL = 2, which is the same "runs every architecture" claim being made good rather than asserted.
One suggestion, downgraded from a condition to a preference
A one-line comment where the block used to be — "AMD's tree has no top-k unmasking here; the fork's copy was pre-merge" — would stop the next person re-adding it. Not required now that the description carries the table, which is why I am not making it a condition any more.
Ready at 4e1deb2. And the useful part of my mistake for the record: when a PR says "restore", the reference it names is the one to measure against — not the nearest commit that happens to predate the change.
…#381) Both removals are deletions of pre-#327 fork code, not restores of it: AMD's design (9bf5871) replaced each one, and #327 kept the old next to the new. A comment at each site says so, so the next merge does not re-add them as an omission. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT: READY at 4e1deb2 — the fixture delta is better than what I reviewed, and better than what I suggested
My verdict was at 50beacb. Since then only tests/test-llama-archs.cpp moved (+7/−8) and it went the other way from a skip: the zaya/zamba2 gate came out and the fixture now writes the hparams those two architectures actually need.
Each new hparam is traceable to the model code's own assertion, which is what makes this the right fix rather than a plausible one:
| fixture writes | the model code says |
|---|---|
SSM_CONV_KERNEL = arch == ZAYA ? 2 : 4 |
zaya.cpp:44 — GGML_ASSERT(hparams.ssm_d_conv == 2 && "the CCA graph is written for 2-tap convs") |
ATTENTION_KEY/VALUE_LENGTH = 2*n_embd_head |
zamba2.cpp:97 — const int64_t attn_hidden = 2 * n_embd; |
case LLM_ARCH_ZAYA: // every layer has CCA attention and the MoE |
zaya.cpp:121 — "every layer has both CCA attention and the MoE" |
An assertion in the model is the strongest possible source for a fixture value: if the fixture writes anything else, the test cannot pass, and if the model changes the assertion, the fixture is visibly wrong rather than silently irrelevant.
Measured here, at this head, CPU-only (bhrx2, built from 4e1deb2):
$ ./bin/test-llama-archs
Summary: all 149 test(s) passed rc 0
$ for a in zaya zamba2 blackmamba qwen4exp; do ./bin/test-llama-archs -a "^$a$"; done
zaya rc=0 zamba2 rc=0 blackmamba rc=0 qwen4exp rc=0 (each: all 1 test(s) passed)
That is more coverage than my previous READY, where those two architectures were skipped: they are now exercised and green, not counted-but-absent.
So I withdraw the one note I made last time — that a known_fail label was the right residue for the skip. It was the right mechanism for a skip; the wrong thing to want was the skip. Restoring the hparams is strictly better, and the engine#2444 FIXME is no longer needed at all.
Unchanged from my earlier review, still verified: build_attn_qsa is byte-identical to AMD's tree (9bf5871) — 77 lines, 0 differing lines; ggml_sigmoid(ctx0, inject) at :431 matches AMD's :426; blackmamba reads the expert array at :31 and splits on n_ff(i) == 0 at :58/:94, which llama-hparams.cpp:66 resolves as n_ff_arr[il].
|
To the CHANGES at 50beacb: you are right about the framing. Fixed at cf0e7fb the second way you offered (keep the deletions and say so). Title and body now say "drop two pre-#327 blocks AMD's design replaced", not "undo slips". Each site has a one-line comment saying why the old code is absent. The reason for each, checked against 9bf5871 rather than argued:
To the harness suggestion (READY at 18:45Z): agreed that one abort hiding every later row is how the BlackMamba slip stayed invisible. Two parts:
|
|
Measured at I rebuilt Two more rows than the What I keep, as a note and not a gate: the table still truncates on a death — at the tip with your model fixes absent it printed ~80 arch rows, died at The |
|
VERDICT at cf0e7fb: READY — and it needs no re-review, because this head is byte-identical to the one I measured. So the re-push changed the commit, not the content, and the measurement I posted on — built from the tip The two One note that is not a gate: the arch table still truncates on a death (at the tip, with your model fixes absent: ~80 rows, died at |
|
VERDICT: READY at Code-identical, not byte-identical, and that is the right kind of identicalBetween So the code is AMD's, and the prose is the fork's — which is exactly the arrangement I would want: the behaviour converges on the reference, and the explanation of what #327 got wrong lives where the next reader looks. A fix that made the bytes match and dropped the reasoning would be worse, and a fix that changed the code and matched the comment would be the original bug again. Both FIXMEs are now modelled rather than excused — better than what I asked forMy ask was for the row to report how much it exercised while if (arch == LLM_ARCH_ZAMBA2) {
// the shared attention block runs on [hidden, embedding] concatenated: q/k/v are 2*n_embd wide
ms.add_kv(LLM_KV_ATTENTION_KEY_LENGTH, 2*n_embd_head);
ms.add_kv(LLM_KV_ATTENTION_VALUE_LENGTH, 2*n_embd_head);
}
ms.add_kv(LLM_KV_SSM_CONV_KERNEL, uint32_t(arch == LLM_ARCH_ZAYA ? 2 : 4)); // zaya: the CCA graph is 2-tapEach is the specific hparam the architecture actually reads, with the reason in the comment — not a blanket skip. That is the durable version of the count: a hybrid that is silently unmodelled is now the only way to be wrong. One small thing, then it is doneThe honest way to close my count ask without re-opening it: have the row print the number it covered ( Everything else stands from my earlier verdict: |
bong-water-water-bong
left a comment
There was a problem hiding this comment.
VERDICT: READY at cf0e7fb
Three comment lines, and I checked what each one points at rather than that it reads well.
Why the identity check still holds, stated as a measurement rather than a claim. At 4e1deb2 I verified build_attn_qsa was byte-identical to AMD's 9bf5871 — 77 lines, 0 differing. This head adds two comment lines inside that function, so the raw diff is no longer empty and the honest number is:
381@cf0e7fb: 79 lines vs AMD 77
diff: < two comment lines (43,44d42)
non-comment differences: 0
Which is the useful half: the code is still AMD's, and the only thing separating them is commentary. A reviewer who greps this later sees a diff and should know it is inert.
Comment 1 — the double scale. "inject arrives scaled by 1/hc (both branches above); the pre-#327 sigmoid(inject / hc) here scaled it twice." Traced to the code it names:
// build_hc_mix:377
// scale the combined rows before the split; both lo and inject use 1/hc
lo_inject = ggml_scale(ctx0, lo_inject, 1.0f / (float) hc);The comment already existed above the scaling and says the same thing the new one relies on — so the new note is not folklore, it restates a property the function above established. That is the difference between "the /hc went away" and "the /hc was already applied".
Comment 2 — the scatter that could not build. "no top-k scatter into kq_mask here: build_qsa_sel already returns the mask. The pre-#327 index scatter (kq_mask_top_k) that #327 kept fed this mask to ggml_set_rows as indices and could not build (engine#2444)." That is the explanation my last review was missing: the block was not merely stale, it was type-wrong — a mask passed where indices belong — which is exactly the GGML_ASSERT(c->type == GGML_TYPE_I64 || …) in this PR's own table. Naming engine#2444 there means the next reader of that assert lands on the reasoning.
Behaviour is unchanged from the head I measured: +3 comment lines only, so test-llama-archs at 4e1deb2 — all 149 test(s) passed — stands as the measurement for this code.
One wording note, not a blocker: "both branches above" reads as above within this function, and within build_hc_combine the only scaling is the comment itself — the actual 1/hc is at the callers' two mix paths (build_hc_mix:378, reached from the attention and FFN call sites at :545/:559 and :670/:675). Saying "both mix branches, in build_hc_mix" would save the next reader the grep.
|
New head: a flake I introduced at 4e1deb2, caught before merge. I turned zaya on in that commit. While building the one-process-per-architecture harness I ran the suite several times, and one run failed: zaya's chunked and mixed decodes are never bit-identical (about 1e-8), and its top-1 router over Whether the 1e-8 itself is a zaya bug (its CCA state across chunks) is still open under ggml-org#2444. A routing flip only shows that it is not bit-identical. |
Refs engine#2444. This fixes the fork side; the engine pin bump follows once this merges.
What was broken
On
1bit/hrx-vulkan-patchedsince #327, Qwen3.8-Flash-Next (qwen4exp) does not load at all, and the CPUctesthas three failures that are not environment:llama-completion -m Qwen3.8-Flash-Next-UD-IQ4_XS … -ngl 0 --temp 0 -p "The capital of France is" -n 16128125e02Paris. The capital of Germany is Berlin. The capital of Italy is Rome.9bf5871aloneParis. The capital of Germany is Berlin. The capital of Italy is Rome.550d06f92ggml.c:4084 GGML_ASSERT(c->type == GGML_TYPE_I64 || c->type == GGML_TYPE_I32)inggml_set_rowsfrombuild_attn_qsa\n\nThe\n\n\n\n##Paris. The capital of Germany is Berlin. The capital of Italy is Rome.All five runs are CPU-only (
GGML_HRX=OFF) with identical flags. The only thing that differs between the rows is the tree.qwen4exp: two DELETIONS of pre-#327 code, each one replaced by AMD's design
These are not restores of the pre-#327 fork. Both blocks existed in
128125e02, and this PR removes them because AMD's tree (9bf5871) redesigned the code around them, and #327 kept the old next to the new:build_attn_qsa(kq_mask_top_k). In the pre-engine#2138 -- AMD pin 9bf5871 merged into 1bit/hrx-vulkan-patched #327 fork,build_qsa_selreturned top-k indices and this block scattered them into the kq mask. In AMD's design,build_qsa_selreturns the[n_kv, n_tokens]mask itself (fusedggml_top_k_maskand unfused set_rows paths alike), andbuild_attn_qsapasses it straight tobuild_attn_mha. engine#2138 -- AMD pin 9bf5871 merged into 1bit/hrx-vulkan-patched #327 took AMD'sbuild_qsa_selbut kept the old consumer, which fed the mask toggml_set_rowsas indices. That node cannot build (GGML_ASSERT(c->type == I64 || I32)), and its result was never used. Removed:build_attn_qsais now byte-identical to 9bf5871's. Nothing consumes indices, soggml_top_k_maskneeds no index output.glm5-next.cppis identical to AMD's and passes.1/hcinbuild_hc_combine,sigmoid(inject / hc). In AMD's design the 1/hc scale moved upstream into the projection that producesinject, in both the fused down+inject branch and the unfused branch ("both lo and inject use 1/hc"). engine#2138 -- AMD pin 9bf5871 merged into 1bit/hrx-vulkan-patched #327 kept AMD's pre-scaledinjectand the fork's/hc, soinjectwas scaled by 1/hc². That is the "loads, then\n\nThe\n\n\n\n##" row. With AMD'ssigmoid(inject), the output equals both reference trees. I bisected this by swapping only that line into the tip.Each site now carries a one-line comment saying why the old code is absent (third commit), so the next merge does not re-add it as an omission.
BlackMamba
blackmamba.cppreadexpert_feed_forward_lengthwithget_keyinton_ff_exp_arr[0]. The model saver writes the per-layer array ([384, 0]in the fixture), so a saved model did not load back (has wrong type arr but expected type u32). It now usesget_key_or_arr(…, n_ff_exp_arr, n_layer_all)like every other MoE architecture. The realBlackMamba-2.8B-IQ4_XS-imx.ggufgenerates byte-identical 24-token greedy text here and on the pre-#327 tree (md522e98bd683cfboth).test-llama-archs
moe_mandatory). Its fixture writes a per-layern_ffof[0, n_ff], since a layer withn_ff == 0is the Mamba mixer. Without a 0, no mixer is built and the recurrent-state input has no buffer atset_input.n_ff_expis 0, so the load fails on a 0-wide tensor) and its CCA graph is 2-tap: MoE-only, withssm.conv_kernel = 2. zamba2's shared attention runs on[hidden, embedding]concatenated, so q/k/v are 2·n_embd wide: the fixture writes key/value lengths of2*n_embd_head. Both now run; nothing is skipped. (Second commit 4e1deb2.)Measured (CPU-only Release build of this head,
ctest -j 6under thermal-run)I also ran each of the 174 architecture names in
llama-arch.cppalone throughtest-llama-archs -a '^name$', so a single abort could not hide the ones after it. Only zamba2 and zaya failed, and the second commit fixes their fixtures. Run in one go,test-llama-archsnow covers all 174 architectures with 0 failures.Not run: HRX device runs. This is a CPU-graph fix. The removed nodes were dead, and the hc line now matches AMD's.
🤖 Generated with Claude Code