 Bi Xue
|
c43716a357
|
[sgl] provide an option to send control req to all dp ranks rank0 (#22758)
|
2026-04-16 14:24:26 +08:00 |
|
|
Bi Xue
|
070c6a2489
|
[sgl] perf optimization for eplb (#21232)
|
2026-04-14 22:52:17 +08:00 |
|
|
Bi Xue
|
d30b3efa84
|
[sgl] _ATTN_TP and _ATTN_CP use message queue for broadcast on CPU (#22205)
|
2026-04-10 20:52:49 -07:00 |
|
|
Bi Xue
|
f652135d52
|
[sgl] fix using symmetric memory issues for attention_tp (#22286)
|
2026-04-11 00:26:18 +08:00 |
|
|
Bi Xueandyilian49
|
52801ff20c
|
[sgl] two potential spec_v2 bug fixes (#21589)
Co-authored-by: yilian49 <yilian49@users.noreply.github.com>
|
2026-04-05 19:41:43 -07:00 |
|
|
Bi Xue
|
42c46e6334
|
[sgl] disable piecewise cuda graph when a model doesn't have layers (#21565)
|
2026-03-29 23:04:20 +08:00 |
|
|
Bi Xue
|
30397e0a1e
|
[rl][sgl] fix tensor mismatch after pause (#21514)
|
2026-03-27 23:02:30 +08:00 |
|
|
|
73bf2c5bdc
|
[sgl]add pin_mem to remove cpu->gpu copy sync point (#19795)
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
|
2026-03-03 21:00:51 -08:00 |
|
|
Bi Xue
|
eaf18ebe8d
|
[sgl]add pin_mem to avoid cpu->gpu copy sync point (#19590)
|
2026-03-02 21:08:31 +08:00 |
|
|
Bi Xue
|
bf36aa4c31
|
[sgl] view could hold the memory too long and introduced large memory (#19109)
|
2026-02-21 23:40:56 +08:00 |
|