Repository navigation
third_party/llama.cpp: pin to 8aa770fbd -- a DFlash draft no longer aborts llama-server's memory fit (llama.cpp#397) - #2526
Conversation
…borts llama-server's memory fit (llama.cpp#397) 6b9fcacb7 -> 8aa770fbd: llama.cpp#394 (tests for #393's loader hunk), #395 (the placement report names BY DESIGN off-HRX nodes, engine#2450), #396 (a buffer type must have an identity, engine#2500) and #397. #397: `1bit serve --dflash` on Qwen3.8-27B + DFlash2 q8_0 aborted at load in the memory-fit probe (GGML_ASSERT ctx_other, src/models/dflash.cpp:944). The draft context now fails to create there and the fitter fits the target alone. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
|
VERDICT: READY The pin's contents are correctly described, and I can corroborate one of them from the inside: #395 (the placement report names BY DESIGN off-HRX nodes, en…) is a PR I reviewed — its whole point was that the engine already classified by-design nodes ( Two asks:
And one thing worth noting for the record: |
|
VERDICT at c4461e4: READY. Four commits, three of which I reviewed this morning — including one where my CHANGES arrived before the merge, which I verified at the pin rather than in the PR thread. My
|
PR Reviewer Guide 🔍Here are some key observations to aid the review process:
|
|
Verdict as an issue comment: the shared identity already holds a pending review on this PR, so VERDICT: READY to merge on the pin rule -- and one measured finding inside it: the test #394 brings is a row nothing runsThe pin itself is right: But I checked what CI does with the test that arrives in this pin, because a test is only worth its row:
So the row added by #394 exits 77 Two asks, both one line:
Nothing else: the pin's own rule ("no new failure vs main's own pin") is satisfied, #394's guard bodies ( |
Correction to my review above: "add the row to the no-device group" would not have made it fail — I measured itI claimed the fix was to put Measured on ctest 4.2.3 on this box, four shapes (
Shipped as llama.cpp#400
#400 is against Unchanged and still the bigger half: nothing passes this row a model -- |
6b9fcacb7 -> 8aa770fbd: llama.cpp#394 (tests for #393's loader hunk), #395 (the placement report names BY DESIGN off-HRX nodes, engine#2450), #396 (a buffer type must have an identity, engine#2500) and #397.
#397:
1bit serve --dflashon Qwen3.8-27B + DFlash2 q8_0 aborted at load in the memory-fit probe (GGML_ASSERT ctx_other, src/models/dflash.cpp:944). The draft context now fails to create there and the fitter fits the target alone. Found by the 27B re-measure (~/briefs/27B-REMEASURE-STATE.md).Commit by cl-hrxkern; pushed from the orchestrator (the lane's push was refused by its permission check). Pin PRs merge on the hw-gate rule: no new failure vs main's own pin.
🤖 Generated with Claude Code