Commits · 51a9fa1dbddd74558472881f616a7fb79759fd24 · yangql / composable_kernel

"...csrc/git@developer.sourcefind.cn:change/sglang.git" did not exist on "ed1044ac1b89495d4236b536316f3d8575de9d21"

26 Sep, 2019 5 commits
- removing dependency on old tensor descriptor · 51a9fa1d
  Chao Liu authored Sep 26, 2019
  
  51a9fa1d
- added type conversion in threadwise and blockwise copy · 0f52c4c0
  Chao Liu authored Sep 26, 2019
  
  0f52c4c0
- added type conversion in threadwise and blockwise copy · b3d4595f
  Chao Liu authored Sep 25, 2019
  
  b3d4595f
- removing old implementation of tensor descriptor · 3cb2a7d0
  Chao Liu authored Sep 25, 2019
  
  3cb2a7d0
- removing old implementation of tensor descriptor · 39d92e7d
  Chao Liu authored Sep 25, 2019
  
  39d92e7d
25 Sep, 2019 3 commits
- clean up · 012b5253
  Chao Liu authored Sep 25, 2019
  
  012b5253
- added GetLinearDimensionMask · e1ae8f18
  Chao Liu authored Sep 25, 2019
  
  e1ae8f18
- adding GetLinearDimensionMask() · 4f4aba48
  Chao Liu authored Sep 24, 2019
  
  4f4aba48
24 Sep, 2019 1 commit
- refactor · 545d9305
  Chao Liu authored Sep 24, 2019
  
  545d9305
22 Sep, 2019 3 commits
- nvidia build · 37f4e2b6
  Chao Liu authored Sep 22, 2019
  
  37f4e2b6
- done: explicitly separate offset component into compile-time, block-invariant... · 6c2c50b0
  Chao Liu authored Sep 22, 2019
```
done: explicitly separate offset component into compile-time, block-invariant and per-thread components. Experimenting
```
  6c2c50b0
- WIP: explicitly separate offset component into compile-time, block-invariant... · 51884fc2
  Chao Liu authored Sep 21, 2019
```
WIP: explicitly separate offset component into compile-time, block-invariant and per-thread components
```
  51884fc2
21 Sep, 2019 3 commits
- refactor · 740da00a
  Chao Liu authored Sep 20, 2019
  
  740da00a
- nvidia build · 184c6e7d
  Chao Liu authored Sep 20, 2019
  
  184c6e7d
- adding logic to judge linear dimension · f00c1381
  Chao Liu authored Sep 20, 2019
  
  f00c1381
20 Sep, 2019 1 commit
- refactor · bf7e7d62
  Chao Liu authored Sep 19, 2019
  
  bf7e7d62
19 Sep, 2019 1 commit
- use buffer_load buffer_store intrinsic · b6e1c52a
  Chao Liu authored Sep 19, 2019
  
  b6e1c52a
18 Sep, 2019 6 commits
- reduce some register usage in index · 8afbb10d
  Chao Liu authored Sep 18, 2019
  
  8afbb10d
- refactor · 94bb1b48
  Chao Liu authored Sep 18, 2019
  
  94bb1b48
- add global_load and buffer_load inline asm · 86cc678f
  Chao Liu authored Sep 18, 2019
  
  86cc678f
- experimenting global and buffer load/store · 5b7a18c5
  Chao Liu authored Sep 18, 2019
  
  5b7a18c5
- experimenting global and buffer load/store · c7a6545e
  Chao Liu authored Sep 18, 2019
  
  c7a6545e
- experimenting global and buffer load/store · 9f46cdf5
  Chao Liu authored Sep 18, 2019
  
  9f46cdf5
17 Sep, 2019 4 commits
- enable hip compiler flag: -amdgpu-enable-global-sgpr-addr · f58bf384
  Chao Liu authored Sep 17, 2019
  
  f58bf384
- bug fix · 126cae0c
  Chao Liu authored Sep 17, 2019
  
  126cae0c
- refactor · e1a67b69
  Chao Liu authored Sep 17, 2019
  
  e1a67b69
- refactor · f7be86b9
  Chao Liu authored Sep 16, 2019
  
  f7be86b9
16 Sep, 2019 1 commit
- bug fix · d7079939
  Chao Liu authored Sep 15, 2019
  
  d7079939
15 Sep, 2019 5 commits
- amd build · 69fea593
  Chao Liu authored Sep 15, 2019
  
  69fea593
- add lds doble buffer to nchw padded v4r1 and v4r4 · 940949d9
  Chao Liu authored Sep 15, 2019
  
  940949d9
- add lds doble buffer to nchw padded v4r1 and v4r4 · bf975428
  Chao Liu authored Sep 15, 2019
  
  bf975428
- initial implementation for nchw v4r4 padding · 2c93b305
  Chao Liu authored Sep 15, 2019
  
  2c93b305
- clean up · 53094f7f
  Chao Liu authored Sep 15, 2019
  
  53094f7f
14 Sep, 2019 1 commit
- initial padding support for nchw · d4878d99
  Chao Liu authored Sep 13, 2019
  
  d4878d99
12 Sep, 2019 2 commits
- clean up · bd7a2300
  Chao Liu authored Sep 12, 2019
  
  bd7a2300
- padding for chwn is functional · 1f705244
  Chao Liu authored Sep 12, 2019
  
  1f705244
11 Sep, 2019 1 commit
- enabling padding for chwn format · 724e984b
  Chao Liu authored Sep 11, 2019
  
  724e984b
10 Sep, 2019 1 commit
- adding merge transform · ca42e910
  Chao Liu authored Sep 10, 2019
  
  ca42e910
09 Sep, 2019 1 commit
- more utility code · 7a7fe160
  Chao Liu authored Sep 09, 2019
  
  7a7fe160
06 Sep, 2019 1 commit
- added tuple · 625838de
  Chao Liu authored Sep 06, 2019
  
  625838de