feat: wire gpu backend#1
Merged
Merged
Conversation
…efines Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
…ation pending Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
On-hardware validation (plan Task 7) complete on an NVIDIA GB10 (Grace
Blackwell, CUDA 13.0, compute capability 12.1):
- GPU backend activates; weights realized in VRAM
- rfdetr-base F16: 23.6 ms/image median (vs 274 ms same-box ARM CPU) = 11.6x
- detections match CPU baseline 8/8 within tolerance (score <=0.05, bbox <=2px)
- the 3 deformable-attention CUSTOM ops confirmed running on CPU via the
scheduler fallback (GGML_SCHED_DEBUG=2)
Flips the README/BENCHMARK GPU status from 'validation pending' to validated
with real numbers.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This wires Nvidia/Metal/Vulkan/Hipblas