Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions .gitignore
Original file line number Diff line number Diff line change
Expand Up @@ -6,3 +6,4 @@ dist
.idea
.vscode
tmp/
.claude
4 changes: 0 additions & 4 deletions lightllm/__init__.py
Original file line number Diff line number Diff line change
@@ -1,4 +0,0 @@
from lightllm.utils.device_utils import is_musa

if is_musa():
import torchada # noqa: F401
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "256": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "256": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 2}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "256": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 10}, "256": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 7}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 7}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 11}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 7}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 11}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 7}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 9}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}}}
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 16, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}}}
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 16, "num_stages": 4}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 2}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 10}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Original file line number Diff line number Diff line change
@@ -0,0 +1 @@
{"4096": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 10}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 4}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}}}
Original file line number Diff line number Diff line change
@@ -1 +1 @@
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 4, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
{"4096": {"8": {"BLOCK_N": 64, "num_warps": 8, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 2}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}, "8192": {"8": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 1}, "32": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 3}, "128": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}, "256": {"BLOCK_N": 16, "num_warps": 2, "num_stages": 5}}}
Loading