The GitHub Actions job "tvm-bot" on tvm.git/main has succeeded.
Run started by GitHub user elvin-n (triggered by elvin-n).

Head commit for run:
b3439430e7e78b2507db9885ab2668d622ecd973 / Ruihang Lai <[email protected]>
[Relax][Frontend][KVCache] Restructure kv_cache kernels (#19405)

Pure refactor — does not change any generated TIR / kernel behavior.

Dedupe the tiled prefill kernels in kv_cache.py by extracting the shared
online-softmax pieces as T.macro helpers (init_states, compute_s_gemm,
softmax_update_{causal,valid_length}, compute_o_gemm,
advance_tile_batch, paged_store_output_lse), plus Python helpers for the
common buffer allocations (softmax state, MHA/MLA Q/K/V/O, tile-walk
scalars).

Split the kernel factories out of kv_cache.py into private sibling
modules: _kernel_common.py (shared helpers + macros + schedule),
_page_kernels.py (append/debug/copy/compact), _prefill_kernels.py
(paged/ragged/MLA/dense/masked-sequence), _decode_kernels.py (decode +
state merge). kv_cache.py now holds only the PagedKVCache classes and
re-exports every moved symbol so existing imports keep working.
tree_attn.py also switches to the shared helpers.

kv_cache.py drops from 2815 to 668 lines; the package is ~2.4k lines
smaller overall. No test files modified; GPU tests pass unchanged (72
passed, 4 pre-existing skips).

Report URL: https://github.com/apache/tvm/actions/runs/24468664402

With regards,
GitHub Actions via GitBox


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to