3 people 4ac0d0eac2 [ROCm][RDNA3] Fix W4A16 split-K accuracy and determinism (#54706) ...

Signed-off-by: AIwork4me <AIwork4me@users.noreply.github.com>
Co-authored-by: AIwork4me <AIwork4me@users.noreply.github.com>
Co-authored-by: JartX <sagformas@epdcenter.es>

2026-10-03 23:44:17 +08:00

..

nvfp4_utils.py

…

test_aiter_hipb_mm_linear_kernel.py

…

test_awq_triton.py

…

test_awq.py

…

test_block_fp8.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_cpu_fp8_scaled_mm.py

…

test_cutlass_scaled_mm.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_cutlass_w4a8_moe.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_cutlass_w4a8.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_flashinfer_mxfp8_trtllm.py

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

test_flashinfer_nvfp4_scaled_mm.py

…

test_flashinfer_scaled_mm.py

…

test_fp8_min_max_helper.py

…

test_fp8_quant_group.py

…

test_fp8_quant.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_gptq.py

…

test_hadacore.py

…

test_int4_emulation_moe.py

[Quant] Use canonical N-first weight format for CT WNA16 MoE (#52798)

2026-09-28 11:22:44 -06:00

test_int8_kernel.py

…

test_int8_quant.py

…

test_machete_mm.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_marlin_gemm.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_marlin_tile_padding.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_mxfp4_kernel_selection.py

[Kernel] Add opt-in load-time MXFP4 dequantization (#50814)

2026-09-22 14:51:12 +08:00

test_mxfp4_qutlass.py

…

test_mxfp4_triton_ep.py

…

test_mxfp6_kernel_selection.py

…

test_mxfp8_kernel_selection.py

[Bugfix][Quantization] Fix MXFP8 startup crash on layers below mm_mxfp8 shape limits (#54223)

2026-09-25 02:54:11 +00:00

test_nvfp4_emulation.py

Disable mypy arg-type and assignment checks in tests (#59428)

2026-09-30 15:18:50 +00:00

test_nvfp4_kernel_selection.py

…

test_nvfp4_quant.py

…

test_nvfp4_qutlass.py

…

test_nvfp4_scaled_mm.py

…

test_per_token_group_quant.py

[Kernel][Perf] Register-resident path for per-token-group 8-bit quant (#55330)

2026-09-25 08:11:42 -07:00

test_quant_op_schema.py

…

test_quantized_embedding.py

…

test_rdna3_compile_guards.py

…

test_rdna3_moe_w4a16.py

…

test_rdna3_w4a16_determinism.py

[ROCm][RDNA3] Fix W4A16 split-K accuracy and determinism (#54706)

2026-10-03 23:44:17 +08:00

test_rdna3_w4a16_selection.py

…

test_rdna3_w4a16.py

…

test_rdna_hybrid_w4a16.py

…

test_rocm_aiter_grouped_quant.py

…

test_rocm_compressed_tensors_w4a16.py

…

test_rocm_fp8.py

…

test_rocm_mxfp4.py

[ROCm] Fix CI runtime and tests for MI355 DPX (#58244)

2026-09-24 23:15:11 -05:00

test_rocm_mxfp8_linear.py

[ROCm][CI] Pass weight_shape in MXFP8 block32 linear tests (#58698)

2026-09-25 10:52:15 +00:00

test_rocm_skinny_gemms.py

[ROCm] Fix CI runtime and tests for MI355 DPX (#58244)

2026-09-24 23:15:11 -05:00

test_scaled_mm_kernel_selection.py

[MyPy][2/N] Fix mypy errors in small tests/ dirs (#51043)

2026-09-29 21:27:45 +01:00

test_silu_mul_nvfp4_quant.py

…

test_triton_scaled_mm.py

…

test_triton_w4a16.py

…

test_w4a16_kernel_selection.py

…

test_zen_da8w4.py

[CPU][Zen] Add DA8W4 (W4A8) int4 support for dense and MoE layers (#54024)

2026-10-01 15:18:25 +08:00