Commits · 966eedc2f72f832083e4011c3f73f2ebcf501856 · OpenDAS / FlashMLA

26 Feb, 2025 3 commits
- Fix readme · 966eedc2
  Jiashi Li authored Feb 26, 2025
  
  966eedc2
- Merge pull request #45 from yangsijia-serena/main · 01d6d400
  Jiashi Li authored Feb 26, 2025
```
fix(benchmark): store 'compare' and 'one' perf results in csv files and visualize them
```
  01d6d400
- add Community Support of [MetaX] and [Moore Threads] · 6492cabb
  hpp authored Feb 26, 2025
  
  6492cabb
25 Feb, 2025 4 commits
- fix(benchmark): store 'compare' and 'one' perf results in csv files and visualize them · b6798030
  yangsijia.614 authored Feb 25, 2025
  
  b6798030
- cuda12.8 recommendation · 4edea86f
  ljss authored Feb 26, 2025
  
  4edea86f
- Merge pull request #32 from sijiac/fp16-support · b549289f
  Jiashi Li authored Feb 25, 2025
```
Support FP16 dtype in FlashMLA kenrel
```
  b549289f
- Style fix · e1e9fa98
  ljss authored Feb 25, 2025
  
  e1e9fa98
24 Feb, 2025 15 commits
- add flag to disable FP16 compile · a3b74b85
  Sijia Chen authored Feb 24, 2025
  
  a3b74b85
- Merge pull request #35 from KnowingNothing/main · 18e32770
  Jiashi Li authored Feb 25, 2025
```
feat: add benchmark for flash_infer vs flash_mla
```
  18e32770
- Merge pull request #37 from chunyang-wen/Update-doc-string · 7d69520a
  Jiashi Li authored Feb 25, 2025
```
Update docstring
```
  7d69520a
- add gitignore for png and csv files in benchmark · 922f63bd
  zhengsize authored Feb 24, 2025
  
  922f63bd
- Update docstring · c4c5912b
  chunyang.wen authored Feb 25, 2025
  
  c4c5912b
- feat: add benchmark for flash_infer vs flash_mla · 4da4dbd3
  zhengsize authored Feb 24, 2025
  
  4da4dbd3
- support fp16 · 65fb7732
  Sijia Chen authored Feb 24, 2025
  
  65fb7732
- replace c10 optional with std optional · 15a82b81
  Sijia Chen authored Feb 24, 2025
  
  15a82b81
- Merge pull request #9 from homorunner/main · bcb90f2a
  Jiashi Li authored Feb 24, 2025
```
support Windows build
```
  bcb90f2a
- Merge pull request #14 from lancerts/minor-fix · dd1161e3
  Jiashi Li authored Feb 24, 2025
```
minor fix test
```
  dd1161e3
- minor fix test · 4fbaa952
  lancerts authored Feb 23, 2025
  
  4fbaa952
- Merge pull request #12 from sazczmh/main · accc1695
  Jiashi Li authored Feb 24, 2025
```
tests: Triton 3.2.0 had remove the fast_flush parameter from do_bench 
```
  accc1695
- support Windows build · e62bdb4d
  程元 authored Feb 24, 2025
  
  e62bdb4d
- tests: Triton had remove the fast_flush parameter from do_bench (#4485) · 051e40e8
  sazc authored Feb 24, 2025
  
  051e40e8
- Initial commit · 414a2f3e
  Jiashi Li authored Feb 21, 2025
```
i
```
  414a2f3e