Fix StreamingTensorInfo.nBytes Int overflow for tensors > 2 GB#459
Merged
michalharakal merged 1 commit intodevelopfrom Apr 8, 2026
Merged
Fix StreamingTensorInfo.nBytes Int overflow for tensors > 2 GB#459michalharakal merged 1 commit intodevelopfrom
michalharakal merged 1 commit intodevelopfrom
Conversation
Change nBytes from Int to Long to prevent silent overflow when computing byte sizes for large tensors (e.g., Gemma 4 E4B per_layer_token_embd.weight). Root cause: `(numBlocks * typeSize).toInt()` silently truncated a Long result exceeding Int.MAX_VALUE, producing negative byte counts that caused `IllegalArgumentException: Length must be non-negative` in JvmRandomAccessSource.readAt(). Changes: - StreamingTensorInfo.nBytes: Int → Long - StreamingGGUFReader: keep nBytes computation in Long, no .toInt() - StreamingGGUFReader.loadTensorData: explicit check with clear error message for tensors > 2 GB (use loadTensorStorageMapped instead) - GGUFReader (legacy): add overflow guard with actionable error message - Update all test comparisons for Long nBytes Fixes #452 Co-Authored-By: Claude Opus 4.6 (1M context) <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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Change nBytes from Int to Long to prevent silent overflow when computing byte sizes for large tensors (e.g., Gemma 4 E4B per_layer_token_embd.weight).
Root cause:
(numBlocks * typeSize).toInt()silently truncated a Long result exceeding Int.MAX_VALUE, producing negative byte counts that causedIllegalArgumentException: Length must be non-negativein JvmRandomAccessSource.readAt().Changes:
Fixes #452