Use int64 as indices for set_kv_buffer (#3039)
This commit is contained in:
@@ -296,7 +296,7 @@ def fused_softcap_kernel(
|
||||
n_elements,
|
||||
BLOCK_SIZE: tl.constexpr,
|
||||
):
|
||||
pid = tl.program_id(0)
|
||||
pid = tl.program_id(0).to(tl.int64)
|
||||
block_start = pid * BLOCK_SIZE
|
||||
offsets = block_start + tl.arange(0, BLOCK_SIZE)
|
||||
mask = offsets < n_elements
|
||||
|
||||
Reference in New Issue
Block a user