qazal
bbfe4f80ec
quantize_fp8 kernels in uops ( #16288 )
...
* add tests
* simple UOp kernel is n^2
* fast kernel matching c++, opts_to_apply=()
* remove cpp
* simple o(n) kernel, two passes
* fuse the loops
* works on DEV=CPU
* multi regression test
* fix multi, this can possibly be its own bugfix
* test cleanups
* minimal diff
* match C in UOps
* Revert "match C in UOps"
This reverts commit 0bef740c30 .
* edit test
* match speed with C try 2
* needs_second_gpu
* cleanup
2026-05-22 20:54:06 +09:00
..
2026-02-12 11:09:44 +08:00
2026-05-21 23:51:40 -04:00
2026-05-20 21:19:37 -04:00
2026-05-21 23:51:40 -04:00
2026-05-16 17:21:07 -04:00
2026-04-21 16:46:38 -04:00
2026-05-21 22:20:33 -04:00
2026-05-21 22:20:33 -04:00
2026-05-16 17:21:07 -04:00
2026-05-19 12:42:54 -07:00
2026-04-26 19:58:53 +03:00
2026-05-21 22:20:33 -04:00
2026-05-19 12:42:54 -07:00
2026-02-12 11:09:44 +08:00
2026-05-12 16:39:36 -04:00
2026-05-20 02:02:45 -04:00
2026-02-12 11:09:44 +08:00
2026-04-27 23:12:03 +03:00
2026-05-20 21:19:37 -04:00
2026-05-22 20:54:06 +09:00
2026-05-21 18:37:11 -04:00
2026-05-16 17:21:07 -04:00
2026-05-21 22:20:33 -04:00
2026-04-25 10:44:41 +03:00
2026-05-21 19:39:57 -04:00
2026-04-25 11:53:16 +03:00
2026-05-21 22:20:33 -04:00
2026-04-27 23:12:03 +03:00
2026-05-21 22:20:33 -04:00
2026-05-15 13:31:10 -04:00
2026-05-20 21:19:37 -04:00
2026-05-21 22:20:33 -04:00
2026-05-21 19:39:57 -04:00
2026-05-20 21:19:37 -04:00
2026-02-26 15:16:01 -05:00
2026-04-17 21:56:29 -04:00
2026-02-23 15:59:20 +08:00
2026-03-02 12:19:48 +08:00
2026-03-02 12:19:48 +08:00
2026-05-21 19:39:57 -04:00
2026-02-12 11:09:44 +08:00
2026-05-21 22:20:33 -04:00
2026-05-21 22:20:33 -04:00
2026-02-12 11:09:44 +08:00