Unverified Commit 087a1389 authored by Andreas Karatzas's avatar Andreas Karatzas Committed by GitHub
Browse files

[ROCm][CI] Fix attention backend test flakiness from uninitialized KV cache memory (#31928)


Signed-off-by: default avatarAndreas Karatzas <akaratza@amd.com>
parent c4041f37
......@@ -136,7 +136,7 @@ def create_and_prepopulate_kv_cache(
slot_mapping = common_attn_metadata.slot_mapping
# Create KV cache
kv_cache = torch.empty(
kv_cache = torch.zeros(
2, num_blocks, block_size, num_kv_heads, head_size, dtype=dtype, device=device
)
kv_cache_flat = kv_cache.view(2, -1, num_kv_heads, head_size)
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment