[CI] change spell checker from codespell to typos (#18711)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
This commit is contained in:
@@ -319,7 +319,7 @@ class MambaMixer2(CustomOp):
|
||||
n_groups == 1, # if there was only one group
|
||||
)
|
||||
intermediate_settings = (intermediate_size, 0, False)
|
||||
head_setings = (self.num_heads, 0, False)
|
||||
head_settings = (self.num_heads, 0, False)
|
||||
|
||||
# - the weight already has a "weight_loader" attribute
|
||||
# which set_weight_attrs will raise if we do not
|
||||
@@ -372,7 +372,7 @@ class MambaMixer2(CustomOp):
|
||||
intermediate_settings,
|
||||
group_shard_settings,
|
||||
group_shard_settings,
|
||||
head_setings, # for dt
|
||||
head_settings, # for dt
|
||||
],
|
||||
self.tp_size,
|
||||
tp_rank,
|
||||
|
||||
@@ -516,7 +516,7 @@ def _chunk_state_varlen_kernel(
|
||||
offs_n[None, :] * stride_chunk_states_dstate)
|
||||
else:
|
||||
|
||||
# - this seems repetitve, buts its to help the compiler
|
||||
# - this seems repetitive, buts its to help the compiler
|
||||
if start_idx < pid_c * chunk_size:
|
||||
past_states_ptrs = chunk_states_ptr + (
|
||||
offs_m[:, None] * stride_chunk_states_hdim +
|
||||
|
||||
@@ -219,7 +219,7 @@ def per_token_group_quant_int8(
|
||||
quantized tensor along with the scaling factor used for quantization.
|
||||
|
||||
Args:
|
||||
x: The input tenosr with ndim >= 2.
|
||||
x: The input tensor with ndim >= 2.
|
||||
group_size: The group size used for quantization.
|
||||
eps: The minimum to avoid dividing zero.
|
||||
dtype: The dype of output tensor. Note that only `torch.int8`
|
||||
|
||||
Reference in New Issue
Block a user