fix: correct gqa_decode_attn reduction + add gqa_prefill_attn
- gqa_decode_attn: rewrite to per-KV-head, K in smem - gqa_prefill_attn: new kernel for Q_len > 1 with GQA
This commit is contained in:
@@ -5,7 +5,7 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
available: dict[str, bool] = {}
|
||||
|
||||
for _name in ["gqa_decode_attn"]:
|
||||
for _name in ["gqa_decode_attn", "gqa_prefill_attn"]:
|
||||
try:
|
||||
importlib.import_module(f".{_name}", package=__package__)
|
||||
available[_name] = True
|
||||
|
||||
Reference in New Issue
Block a user