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 219ae85d4b [Runtime Patch] Add AbortSignal to fetchWithCache in
ArtifactCacheTemplate interface (#17233)
add 76b954a09e [3rdparty] Bump FlashInfer (#17236)
add 21c12fb124 [Bugfix][Cutlass] fix cutlass instantiate attention
template bugs (#17229)
add cd09ab64b5 [Runtime] Reorganize PagedKVCache attn kernel invocation
(#17237)
No new revisions were added by this update.
Summary of changes:
3rdparty/flashinfer | 2 +-
python/tvm/contrib/cutlass/attention_operation.py | 2 +-
src/relax/transform/fuse_ops.cc | 2 +-
src/runtime/relax_vm/paged_kv_cache.cc | 163 ++++++++++++---------
..._builtin_paged_attention_kv_cache_flashinfer.py | 13 +-
...runtime_builtin_paged_attention_kv_cache_tir.py | 13 +-
6 files changed, 118 insertions(+), 77 deletions(-)
