ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-05-01 20:21:23 +00:00
Code Issues Packages Projects Releases Wiki Activity

Make CK TILE GEMM Aquant support block tile 128x128x128 (#3325)

Browse Source 
* [CK TILE GEMM Quant] Rename GemmConfigBQuantPrefill to GemmConfigQuantPrefill in examples

* [CK TILE GEMM Quant] update tile distribution of aquant

* [CK TILE GEMM Quant] update aquant register offset calculation

* [CK TILE GEMM Quant] Reimplement aquant register offset calculation

* [CK TILE GEMM Quant] Add more unit tests of Aquant

- Test M128xN128xK128

* [CK TILE GEMM Quant] Add more comments to Gemm Aquant
This commit is contained in:
Cong Ma
2025-12-01 16:04:37 -07:00
committed by GitHub
parent 7873f8fa13
commit 23fb253c4e
11 changed files with 58 additions and 46 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
example/ck_tile/38_block_scale_gemm/README.md
View File

@@ -74,7 +74,7 @@ User need to select correct mapping of config for each quant mode:
|:--------|:-----:|:-----:|-------|
| For selecting AQuant | aquant | gemm_aquant_quantgrouped.cpp| GemmConfigQuantDecode |
| For selecting AQuant with Preshuffle quant | aquant | gemm_aquant_quantgrouped_preshufflequant.cpp | GemmConfigPreshuffleQuantDecode |
| For selecting BQuant | bquant | gemm_bquant_quantgrouped_<prec_type>.cpp| GemmConfigQuantDecode (or) GemmConfigBQuantPrefill |
| For selecting BQuant | bquant | gemm_bquant_quantgrouped_<prec_type>.cpp| GemmConfigQuantDecode (or) GemmConfigQuantPrefill |
| For selecting BQuant with Preshuffle quant | bquant | gemm_bquant_quantgrouped_preshufflequant.cpp| GemmConfigPreshuffleQuantDecode (or) GemmConfigPreshuffleBQuantPrefill |
| For selecting PreShuffle B with BQuant | bquant | gemm_bquant_quantgrouped_preshuffleb.cpp| GemmConfigPreshuffleB_BQuant_Decode (or) GemmConfigPreshuffleB_BQuant_Prefill
| For selecting PreShuffle B with preshuffle BQuant | bquant | gemm_bquant_quantgrouped_preshuffleb_preshufflequant.cpp |GemmConfigPreshuffleB_PreshuffleBQuant_Decode (or) GemmConfigPreshuffleB_PreshuffleBQuant_Prefill