[3/N][warmup][DSv4] Migrate FA4 MLA and shared CuTeDSL kernels (#53565)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com> Co-authored-by: Codex <codex@openai.com> Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
This commit is contained in:
co-authored by
Codex
mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
parent
1713b9866a
commit
42801b3a6b
@@ -2,7 +2,7 @@
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""Correctness test for the Inkling FA4 relative-attention score-mod kernel.
|
||||
|
||||
Checks ``INKLING_FA4_REL_ATTENTION_KERNEL`` against a pure-PyTorch reference
|
||||
Checks ``_INKLING_FA4_REL_ATTENTION_KERNEL`` against a pure-PyTorch reference
|
||||
that implements the relative bias exactly as documented in the Inkling architecture
|
||||
guide::
|
||||
|
||||
@@ -23,7 +23,7 @@ from vllm.models.inkling.nvidia.attention import (
|
||||
compute_log_scaling_tau,
|
||||
)
|
||||
from vllm.models.inkling.nvidia.ops.fa4_rel_attention import (
|
||||
INKLING_FA4_REL_ATTENTION_KERNEL,
|
||||
_INKLING_FA4_REL_ATTENTION_KERNEL,
|
||||
_use_sheared_bias,
|
||||
inkling_fa4_num_splits,
|
||||
)
|
||||
@@ -279,7 +279,7 @@ def _run_case(seq_lens, num_heads, num_kv_heads, rel_extent, window_left, seed=0
|
||||
num_kv_heads=num_kv_heads,
|
||||
max_kv_len=max(kv_lens),
|
||||
)
|
||||
out = INKLING_FA4_REL_ATTENTION_KERNEL(
|
||||
out = _INKLING_FA4_REL_ATTENTION_KERNEL(
|
||||
q,
|
||||
key_cache,
|
||||
value_cache,
|
||||
|
||||
Reference in New Issue
Block a user