Skip to content

Commit ef6b2cf

Browse files
Add ep: 4 for tp=4 entries in dsr1-fp4-b200-sglang config
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
1 parent eb0fedb commit ef6b2cf

1 file changed

Lines changed: 3 additions & 3 deletions

File tree

.github/configs/nvidia-master.yaml

Lines changed: 3 additions & 3 deletions
Original file line numberDiff line numberDiff line change
@@ -9,17 +9,17 @@ dsr1-fp4-b200-sglang:
99
- isl: 1024
1010
osl: 1024
1111
search-space:
12-
- { tp: 4, conc-start: 4, conc-end: 128 }
12+
- { tp: 4, ep: 4, conc-start: 4, conc-end: 128 }
1313
- { tp: 8, ep: 8, conc-start: 4, conc-end: 128 }
1414
- isl: 1024
1515
osl: 8192
1616
search-space:
17-
- { tp: 4, conc-start: 4, conc-end: 128 }
17+
- { tp: 4, ep: 4, conc-start: 4, conc-end: 128 }
1818
- { tp: 8, ep: 8, conc-start: 4, conc-end: 128 }
1919
- isl: 8192
2020
osl: 1024
2121
search-space:
22-
- { tp: 4, conc-start: 4, conc-end: 128 }
22+
- { tp: 4, ep: 4, conc-start: 4, conc-end: 128 }
2323
- { tp: 8, ep: 8, conc-start: 4, conc-end: 16 }
2424

2525
dsr1-fp4-b200-trt:

0 commit comments

Comments
 (0)