 MaciejBalaNV
|
7d6e2ade6c
|
[bugfix] Fix FP8 Quack kernels when using Context Parallelism and reduce number of recompilations (#7458)
Signed-off-by: Maciej Bala <mbala@nvidia.com>
|
2026-09-22 11:38:17 -07:00 |
|
|
SYLARandlishunyang12
|
779466becb
|
[Bugfix][Quant] Skip quack FP8 GEMM when scales are unpopulated (#5262)
Signed-off-by: lishunyang12 <lishunyang03@gmail.com>
Co-authored-by: lishunyang12 <lishunyang03@gmail.com>
|
2026-07-21 10:11:16 +00:00 |
|
|
bastefaniakandRoger Wang
|
07957e12f4
|
Fix FP8 Quack GEMM call when inference_mode() and torch.compile() is used. (#5153)
Signed-off-by: Bartosz Stefaniak <bstefaniak@nvidia.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
|
2026-07-16 15:01:21 -07:00 |
|
|
Renzheng Wang
|
6b11f6b41d
|
[Bugfix][Quant] Gate quack FP8 to datacenter Blackwell (sm_100.x) only (#4817)
Signed-off-by: wangrzneu <wangrzneu@gmail.com>
|
2026-07-01 16:51:17 +00:00 |
|
|
SYLAR
|
b5352a5869
|
[Quant][Perf] Default Blackwell FP8 GEMM to quack CuteDSL fused-bias kernel (#4241)
Signed-off-by: WeiQing Chen <david6666666@users.noreply.github.com>
|
2026-06-08 19:44:20 +00:00 |
|