Aviral Goel b8751e505d feat: Add Interwave scheduler for aquant memory pipeline (#3540) ...

* WIP: host level interwave pipeline compiles

* WIP: interwave implementation computes correct GEMM result when no aquant

* WIP: quantization works for subset of problem shapes

* WIP: quantization works for subset of problem shapes

* WIP: interwave memory pipeline passes local test

* feat: Add interwave pipeline implementation for memory pipline in aquant

* test: add unit test for aquant memory pipeline

* WIP: host level interwave pipeline compiles

* WIP: interwave implementation computes correct GEMM result when no aquant

* WIP: quantization works for subset of problem shapes

* WIP: quantization works for subset of problem shapes

* WIP: interwave memory pipeline passes local test

* feat: Add interwave pipeline implementation for memory pipline in aquant

* fix: compilation error on gfx950

* chore: remove debug statements from the code

* test: resolve merge conflict

* test: remove non rcr unit tests from test suite

2026-01-26 11:27:42 -08:00

..

block_gemm_quant_common.hpp

Support A/B Quantization in Blockscale GEMM (#3343)

2025-12-17 07:13:47 -08:00

block_universal_gemm_ar_aquant_flatbr_bquant_cr.hpp

GEMM Blockscale ABQuant Optimization (#3620)

2026-01-22 09:39:38 -08:00

block_universal_gemm_ar_flatbr_bquant_cr.hpp

Support A/B Quantization in Blockscale GEMM (#3343)

2025-12-17 07:13:47 -08:00

block_universal_gemm_as_aquant_bs_bquant_cr.hpp

GEMM Blockscale ABQuant Optimization (#3620)

2026-01-22 09:39:38 -08:00

block_universal_gemm_as_aquant_bs_cr.hpp

feat: Add Interwave scheduler for aquant memory pipeline (#3540)

2026-01-26 11:27:42 -08:00

block_universal_gemm_as_bs_bquant_cr.hpp

[CK_Tile] Support for group size 128 for Preshuffle quant for 2d block scale gemm (#3462)

2026-01-14 10:00:19 -08:00