Repository navigation
feat(zoo): load the Higgs Audio v2 codec encoder from int8 and int4 checkpoints - #104
Merged
Merged
Conversation
xxpopielxx
force-pushed
the
feat/quant-encoder
branch
from
November 6, 2026 09:10
68bc12d to
ff3ae76
Compare
xxpopielxx
force-pushed
the
feat/quant-encoder
branch
2 times, most recently
from
November 12, 2026 09:03
416fed3 to
6acae1b
Compare
xxpopielxx
force-pushed
the
feat/quant-encoder
branch
from
November 12, 2026 13:28
6acae1b to
adbf10e
Compare
chmjkb
approved these changes
Nov 13, 2026
…heckpoints A Conv1d the quantized matmul cannot run, such as one on a single input channel, loads a quantized weight as its dequantized floats.. The position conv takes a folded weight next to the weight norm. dequantize() gives a QuantTensor's values, and the codec decoder folds its quantized weights with it.
xxpopielxx
force-pushed
the
feat/quant-encoder
branch
from
November 13, 2026 14:07
adbf10e to
9d76687
Compare
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Stacked on #102 (base
feat/quant-codec).Loads the Higgs Audio v2 codec encoder from int8 and int4 checkpoints (format version 2).
Conv1d: a layer that no scale group fits on the quantized conv (in channels not a multiple of 4, or kernel·in not a multiple of 8, e.g. one input channel) loads a quantized weight as its dequantized floats. A wrong group size on a layer that fits still throws.conv.weightnext to the weight norm, so a quantized file loads; each group runs quantized.dequantize()weight helper; the codec decoder's fold uses it instead of its own loop (touches feat(zoo): load the Higgs Audio v2 codec decoder from int8 and int4 checkpoints #102'sdecoder.ts).Introduces a breaking change?
Type of change
Testing instructions
pnpm --filter runntime exec vitest run test/core/nn/layers.test.ts test/core/weights/transforms.test.ts test/zoo/higgspnpm bench:ab kernels -b feat/quant-codec -k conv,matmul: 90 cases, allsame, max abs 0.Screenshots
Related issues
#97, #102
Checklist
Additional notes