Li, Jiang 79f0be21ff [Bugfix][CPU] Fix DeepSeek-R1 (FP8 MLA + MoE) correctness on CPU backend (#56773) ...

Signed-off-by: jiang1.li <jiang1.li@intel.com>

2026-09-14 17:30:28 +08:00

..

__init__.py

[XPU] Add XPU block-scaled W8A8 fp8 path (#39968)

2026-06-03 20:16:19 +08:00

aiter.py

[ROCm][Bugfix] Fix AITER preshuffled FP8 block-scale kernel (#56433)

2026-09-11 11:44:57 +00:00

b12x.py

[Refactor] Simplify B12X linear kernels and warmup (#52368)

2026-08-17 09:45:45 -07:00

BlockScaledMMLinearKernel.py

[Bugfix] Fix DeepGEMM FP8 warmup coverage (#56452)

2026-09-12 14:20:38 -04:00

cpu.py

[Bugfix][CPU] Fix DeepSeek-R1 (FP8 MLA + MoE) correctness on CPU backend (#56773)

2026-09-14 17:30:28 +08:00

cutlass.py

[Perf] SM90 cutlass fp8 mm supports odd M by swap_ab, 180~290% kernel performance improvement (#44572)

2026-06-13 12:05:45 -07:00

deep_gemm.py

[Bugfix] Fix DeepGEMM FP8 warmup coverage (#56452)

2026-09-12 14:20:38 -04:00

flashinfer.py

Add the QuantizedActivation linear-kernel contract (#44260)

2026-06-12 13:48:15 -07:00

humming.py

[Refactor] refactor humming linear and moe backends to use explicit layer configs (#49610)

2026-08-07 10:03:19 -07:00

marlin.py

[Bugfix][Quantization] Support CT block FP8 with Marlin (#52966)

2026-08-19 12:41:26 -07:00

pytorch.py

[Fusion] Manual ActivationQuantFusionPass initial application (#51415)

2026-09-03 13:37:31 -04:00

rocm.py

Enable gfx1250 ROCm architecture (#46516)

2026-07-31 01:41:12 +00:00

ScaledMMLinearKernel.py

Add the QuantizedActivation linear-kernel contract (#44260)

2026-06-12 13:48:15 -07:00

triton.py

[Kernel][XPU] Tensor-descriptor operand loads for Triton W8A8 scaled_mm (#47205)

2026-08-10 00:56:11 +00:00

xpu.py

[XPU] [Bugfix] process ragged weights in xpu linear backend (#52118)

2026-08-14 09:11:43 +08:00

zentorch.py

[CPU][Zen] Route W8A8 and W4A16 linear inference through zentorch on AMD Zen CPUs (#41813)

2026-05-30 14:17:21 -05:00