|
|
c9d5b6d4a8
|
Replace FlashAttention with xformers (#70)
|
2023-05-05 02:01:08 -07:00 |
|
|
|
27f1410d06
|
New weight loader without np copy (#52)
|
2023-05-03 15:32:04 +08:00 |
|
|
|
ee88a7e5f3
|
Add an option to use dummy model weights (#33)
|
2023-04-08 23:36:12 -07:00 |
|
|
|
12659a0bd7
|
Add CUDA graph-based all reduce launcher (#26)
|
2023-04-05 11:16:57 -07:00 |
|
|
|
897cb2ae28
|
Optimize data movement (#20)
|
2023-04-02 00:30:17 -07:00 |
|
|
|
2f49f15585
|
Support tensor parallel (#2)
|
2023-03-21 13:45:42 -07:00 |
|
|
|
cfae35b861
|
Add miscellaneous updates (#8)
|
2023-03-13 13:48:38 -07:00 |
|
|
|
1a7eb7da61
|
Support beam search & parallel generation (#7)
|
2023-03-10 09:58:21 -08:00 |
|
|
|
0deacbce6e
|
Implement single_query_cached_kv_attention kernel (#3)
|
2023-03-01 15:02:19 -08:00 |
|
|
|
1ce1333573
|
Set default dtype to half
|
2023-02-23 21:31:39 +00:00 |
|
|
|
fdd0f2f472
|
Minor
|
2023-02-23 20:23:47 +00:00 |
|
|
|
343cea3dbc
|
Add seq_ids to input metadata
|
2023-02-23 09:25:01 +00:00 |
|
|
|
4b1ac23f53
|
Fix slot mapping
|
2023-02-23 00:10:07 +00:00 |
|
|
|
8290fce47d
|
Add Worker class
|
2023-02-22 19:01:38 +00:00 |
|
