[2/N][Pangu][MoE] Remove Pangu Related Code (#5130)
### What this PR does / why we need it?
Remove Pangu Related Code
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
e2e & ut
- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c
---------
Signed-off-by: weichen <calvin_zhu0210@outlook.com>
This commit is contained in:
@@ -79,15 +79,6 @@ class AscendAttentionBackend(AttentionBackend):
|
||||
) -> Tuple[int, ...]:
|
||||
return (2, num_blocks, block_size, num_kv_heads, head_size)
|
||||
|
||||
@staticmethod
|
||||
def get_bsh_kv_cache_shape(
|
||||
num_blocks: int,
|
||||
block_size: int,
|
||||
num_kv_heads: int,
|
||||
head_size: int,
|
||||
) -> Tuple[int, ...]:
|
||||
return (2, num_blocks, block_size, num_kv_heads * head_size)
|
||||
|
||||
@staticmethod
|
||||
def swap_blocks(
|
||||
src_kv_cache: List[torch.Tensor],
|
||||
|
||||
Reference in New Issue
Block a user