vLLM/tests/kernels/quantization at 5e4e927b5e3a1cc7c1debe11e503a78ea241689f - vLLM

nvfp4_utils.py

[Kernel] Add b12x FP4 MoE backend (#52018 )

2026-08-21 08:04:36 -07:00

test_aiter_hipb_mm_linear_kernel.py

[ROCm][CI] Move ROCm AITER quantization tests (#40938 )

2026-08-18 14:50:35 +08:00

test_allspark_gemm.py

…

test_awq_triton.py

[Kernel][Test] Extend lightning_attn and awq_triton kernel tests to XPU (#43307 )

2026-06-04 14:25:59 -04:00

test_awq.py

[Refactor] Remove dead quantization code and tests (#45454 )

2026-06-17 16:12:01 -04:00

test_block_fp8.py

[Bugfix][Tests] Stabilize B12X linear kernel checks (#54996 )

2026-09-02 18:46:08 +00:00

test_cpu_fp8_scaled_mm.py

…

test_cutlass_scaled_mm.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

test_cutlass_w4a8_moe.py

…

test_cutlass_w4a8.py

…

test_flashinfer_mxfp8_trtllm.py

[Kernel] Add FlashInfer TRTLLM MXFP8 linear backend (#52204 )

2026-08-20 10:07:22 -04:00

test_flashinfer_nvfp4_scaled_mm.py

[Kernel] add Flashinfer cutedsl w4a16 linear (#53014 )

2026-09-01 02:49:14 +00:00

test_flashinfer_scaled_mm.py

…

test_fp8_min_max_helper.py

…

test_fp8_quant_group.py

[Bugfix] Initialize DeepGemmQuantScaleFMT oracle lazily; bound QuantFP8 UE8M0 packed path to group_size 128 (#51359 )

2026-08-12 14:27:50 -04:00

test_fp8_quant.py

…

test_gptq.py

…

test_hadacore.py

…

test_int4_emulation_moe.py

[feature]Add int4 quantization support for emulation moe backend (#48451 )

2026-07-16 02:00:12 +00:00

test_int8_kernel.py

[Misc] Add and enable Triton kernel unit tests on XPU (#45694 )

2026-08-07 02:53:03 -07:00

test_int8_quant.py

…

test_machete_mm.py

…

test_marlin_gemm.py

…

test_marlin_tile_padding.py

[MoE Refactor] Combine CompressedTensorsWNA16MarlinMoEMethod with CompressedTensorsWNA16MoEMethod (#44570 )

2026-07-31 14:13:03 -07:00

test_mxfp4_kernel_selection.py

[Online quantization] Add online MXFP4 quantization support (#49347 )

2026-08-07 12:39:46 -07:00

test_mxfp4_qutlass.py

…

test_mxfp4_triton_ep.py

…

test_mxfp6_kernel_selection.py

[ROCm][Quark][7/N] Use MXFP4 linear kernel abstraction for emulation backend (#48949 )

2026-07-31 10:07:15 -07:00

test_nvfp4_emulation.py

Make bare hugging_face imports forbidden (#49726 )

2026-07-25 04:18:39 -07:00

test_nvfp4_quant.py

[Perf][Kernel] Initialize NVFP4 padding in quant kernel (#53568 )

2026-09-01 09:49:07 -07:00

test_nvfp4_qutlass.py

…

test_nvfp4_scaled_mm.py

…

test_per_token_group_quant.py

[XPU][Tests] Make tests device-agnostic (#51968 )

2026-08-20 02:25:41 -07:00

test_quant_op_schema.py

[ROCm][CI] Move ROCm AITER quantization tests (#40938 )

2026-08-18 14:50:35 +08:00

test_quantized_embedding.py

…

test_rdna3_compile_guards.py

[Refactor] Rename rocm_moe.py to rocm_moe_rdna.py (#45011 )

2026-06-10 17:02:09 +08:00

test_rdna3_moe_w4a16.py

[ROCm][Perf] Fused MoE W4A16 HIP kernel for AMD RDNA3 (gfx1100) (#44075 )

2026-06-06 15:30:39 -05:00

test_rdna3_w4a16_selection.py

…

test_rdna3_w4a16.py

…

test_rdna_hybrid_w4a16.py

[ROCm][Kernel] Add HybridW4A16LinearKernel: Triton prefill + HIP skinny decode (#40977 )

2026-07-13 20:22:00 -07:00

test_rocm_aiter_grouped_quant.py

[ROCm][CI] Move ROCm AITER quantization tests (#40938 )

2026-08-18 14:50:35 +08:00

test_rocm_compressed_tensors_w4a16.py

…

test_rocm_fp8.py

[ROCm][CI] Add More AITER quantization/MoE kernel tests (#49375 )

2026-08-05 21:27:33 +00:00

test_rocm_mxfp4.py

[ROCm] remove VLLM_ROCM_USE_AITER_FP4_ASM_GEMM environment variable; make w4a4 use the preshuffle triton+asm by default (#53141 )

2026-08-28 18:59:53 +00:00

test_rocm_skinny_gemms.py

[ROCm][CI] Speed Up ROCm Skinny GEMM Tests (reduced parameterizations, (#51877 )

2026-08-12 01:40:13 +00:00

test_scaled_mm_kernel_selection.py

…

test_silu_mul_nvfp4_quant.py

…

test_triton_scaled_mm.py

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

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

test_triton_w4a16.py

[Performance] Register Triton W4A16 GEMM as a custom op (#51453 )

2026-09-01 22:55:34 -05:00

test_w4a16_kernel_selection.py

[ROCm][Kernel] Add HybridW4A16LinearKernel: Triton prefill + HIP skinny decode (#40977 )

2026-07-13 20:22:00 -07:00