This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from cd92392d34 [Refactor] Clean up Relay references in the codebase
(#17733)
add a7895a301a [Attention] Added caching for flashinfer binaries during
JIT (#17730)
add 611bf3bcb6 Fix: Change variable i to x in split operation in
cross_compilation_and_rpc.py (#17743)
No new revisions were added by this update.
Summary of changes:
docs/how_to/tutorials/cross_compilation_and_rpc.py | 6 +-
python/tvm/relax/backend/cuda/flashinfer.py | 80 +++++++++++++++++++---
.../test_runtime_builtin_kv_cache_transfer.py | 2 +-
..._builtin_paged_attention_kv_cache_flashinfer.py | 2 +-
...ltin_paged_attention_kv_cache_mla_flashinfer.py | 2 +-
5 files changed, 76 insertions(+), 16 deletions(-)
