ROCm/composable_kernel
1
0
Fork 0
mirror of https://github.com/ROCm/composable_kernel.git synced 2026-04-20 14:59:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Add Memory pipeline for AQuant Block Scale GEMM (#2987)

Browse Source 
* WIP: add memory pipeline boiler plate code that compiles and works for one block

* WIP: tail handling works for memory pipeline

* WIP: numerical errors appears to have gone by adding block_sync_lds()

* fix: numerical error with memory pipeline by adding block_sync_lds() and new tail handler

* refactror: remove debug print statements and lints

* fix: remove redundant sync barriars

* chore: remove lint

* fix: remove unused code from tile handler and remove redundant block_sync_lds()

* fix: correct parent struct name for memory pipeline

* fix: remove static assert check from parent struct and add it to child struct because not all child structs needs to static assert

* fix: defer block sync lds to just before prefill
This commit is contained in:
Aviral Goel
2025-10-08 20:22:30 -04:00
committed by GitHub
parent e29151b533
commit e99356dabc
6 changed files with 489 additions and 12 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
include/ck_tile/ops/gemm_quant.hpp
View File

@@ -11,6 +11,7 @@
#include "ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_base.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_policy.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_v3.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_aquant_pipeline_ag_bg_cr_mem.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_base.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_policy.hpp"
#include "ck_tile/ops/gemm_quant/pipeline/gemm_bquant_pipeline_ag_bg_cr_v3.hpp"