docs(#1205): why the GROUP_128/GROUP_64 native decode kernel was closed - #1214
Merged
Merged
Conversation
…as closed, not built #1205 (native decode kernel for BitNet.cpp's grouped I2_S layout) is closed as not planned: AOT conversion (I2sAotConverter, #1207) already reaches the same zero-copy mmap path (#1203) for a fraction of the ongoing cost of maintaining a second decode variant per SIMD backend, and the layout is a property of which pipeline quantized the file, not which device runs it -- so a native kernel would still need runtime dispatch across every layout regardless of build target. Full reasoning and what a kernel would need if a real use case someday can't tolerate an AOT step: #1205's closing comment. - I2sGgufLayout.GROUP_128/GROUP_64 doc comments point here instead of leaving the decision as tribal knowledge in a closed GitHub issue only. - ternary-getting-started.adoc gains a "Loading a BitNet.cpp-quantized GGUF" section covering the same ground for someone hitting the grouped layout for the first time, plus a Status and roadmap update.
|
📖 Documentation Preview The documentation has been built successfully for this PR. Generated Files:
Artifacts:
This comment will be updated automatically when the PR is updated. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes the doc/code side of #1205 (already closed on GitHub — this PR just makes the reasoning
discoverable in-repo instead of only in a closed issue's comment).
Decision
A native kernel that decodes BitNet.cpp's grouped I2_S layout (`GROUP_128`/`GROUP_64`) directly,
skipping the repack, was considered and closed as not planned — AOT conversion
(`I2sAotConverter`, #1207) already gets a converted file to the same zero-copy mmap path (#1203)
for a fraction of the ongoing cost of maintaining a second decode variant per SIMD backend. Full
reasoning, and what such a kernel would actually need if a real use case someday can't tolerate an
AOT step, is in #1205's closing comment.
What this PR adds
instead of leaving it undocumented in the code someone would actually be reading when they hit
this limitation.
the grouped-vs-sequential layout distinction and pointing at `I2sAotConverter` as the supported
fix, plus a "Status and roadmap" update noting 0.51.0's off-heap/mmap/AOT work and [Deferred] Native decode kernel for BitNet.cpp's GROUP_128 layout (no-repack mmap) #1205's
closure.
Test plan