Repository navigation
bench: CUDA benchmark on Quadro T2000 (4 GB) - #82
Merged
khanhnd61-vr merged 2 commits intoNov 11, 2026
Merged
Conversation
Add the T2000 CUDA report and the checks that let vla.cpp build and run on Turing. Kernels that need a minimum architecture are built for the requested architectures that reach it (BitVLA at sm_75, fused and FoldQuant at sm_80), so an sm_75 build still links. Fused CUDA ops check the device and that the build has a compatible kernel image before creating fused nodes, so sm_75 falls back to the plain ggml CUDA graph, and BitVLA uses its ladder kernels instead of the Ampere MMA path. test_fused_cuda_availability covers the check. vla_predict_check gains VLA_CHECK_SEED and VLA_CHECK_TOKENS for the report's fixed-input checks.
tuanank2112-crypto
force-pushed
the
t2000-cuda-benchmark
branch
from
November 11, 2026 03:24
bce0246 to
e32e9be
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add CUDA benchmark results for NVIDIA Quadro T2000 (4 GB VRAM).