[PD] Refactor parallel sizes and add pp support for mooncake (#8571)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
This commit is contained in:
@@ -25,10 +25,13 @@ class KVArgs:
|
||||
gpu_id: int
|
||||
# for different tp
|
||||
decode_tp_size: int
|
||||
# for pp prefill
|
||||
prefill_pp_size: int
|
||||
kv_head_num: int
|
||||
page_size: int
|
||||
# for pp prefill
|
||||
prefill_pp_size: int
|
||||
pp_rank: int
|
||||
# for system dp
|
||||
system_dp_rank: int
|
||||
|
||||
|
||||
class KVPoll:
|
||||
|
||||
Reference in New Issue
Block a user