4 people 0103a9b96f [Quantization] Add per-token NVFP4 CuTe-DSL MoE backend (#50030) ...

Signed-off-by: aoshen02 <aoshen@inferact.ai>
Signed-off-by: S1ro1 <matej.sirovatka@gmail.com>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>

2026-09-30 10:42:03 +00:00

..

__init__.py

[CI/Build] Move test_utils.py to tests/utils.py (#4425)

2024-05-13 23:50:09 +09:00

reference_mxfp4.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

test_auto_awq.py

[CI] Speed up quantization test group (#53291)

2026-09-01 13:15:24 -05:00

test_auto_gptq.py

[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)

2026-09-08 12:45:12 -07:00

test_auto_round.py

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

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

test_blackwell_moe.py

[Bugfix][MoE] Restore routed output unpadding before shared expert add (#45707)

2026-06-16 16:06:28 +03:00

test_compressed_tensors.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_config_utils.py

[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)

2026-09-04 11:46:06 -07:00

test_configs.py

[Refactor] Remove dead tests utils (#58803)

2026-09-26 09:16:53 -04:00

test_cpu_offload.py

[CI] Split (H200 MIG/MI300) Basic Correctness into named jobs (#57054)

2026-09-25 17:05:33 -07:00

test_cpu_w8a8.py

[CPU] Support cpu compressed-tensor w8a8 int8 moe (#42920)

2026-06-29 03:04:05 +00:00

test_cpu_wna16.py

[CPU][Whisper] Support W4A16 quantized Whisper on the CPU WNA16 kernel (#58268)

2026-09-30 13:52:53 +08:00

test_cutlass_w4a16.py

[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)

2026-09-08 12:45:12 -07:00

test_experts_int8.py

[CI Bug] Fix Chunked prefill is required for mamba cache mode 'align'. (#51177)

2026-08-05 11:33:45 -07:00

test_fp8_per_channel.py

[CI] Speed up quantization test group (#53291)

2026-09-01 13:15:24 -05:00

test_fp8.py

[Bugfix][ROCm] AMD-Quark mixed-precision DeepSeek-V4.1 support (#57071)

2026-09-25 20:51:18 -05:00

test_gfx950_moe.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_gptq_dynamic.py

[Quant][Kernel] Remove GPTQ Group/Dynamic Activation Ordering (#54809)

2026-09-08 12:45:12 -07:00

test_humming_ignore.py

[Bug][Quantization] Fix humming is_layer_skipped for compressed-tensors "re:" ignore entries (#48507)

2026-07-16 07:47:42 -07:00

test_humming_mxfp4_block_fp8.py

[Feature][Humming] Humming feature integration (#56685)

2026-09-20 08:11:01 -07:00

test_int8_moe_oracle.py

[Quantization][XPU] Enable int8_w8a8 MoE on the Triton backend for XPU (#53162)

2026-09-18 22:38:15 +08:00

test_lm_head.py

[Bugfix][Quantization] Give LM heads standard linear metadata (#58444)

2026-09-24 16:39:49 -07:00

test_mixed_precision.py

[CI] Add TP=4 requirement to test_mixed_precision_model_accuracies (#46161)

2026-06-22 18:19:43 -05:00

test_modelopt.py

[Bugfix][Quantization] Give LM heads standard linear metadata (#58444)

2026-09-24 16:39:49 -07:00

test_moe_wna16.py

[Bugfix] Fix moe_wna16 w13 zero-point shard split for 8-bit asym GPTQ MoE (#58950)

2026-09-28 23:38:28 +00:00

test_online_mxfp4.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_online.py

[Quantization] Add per-token NVFP4 CuTe-DSL MoE backend (#50030)

2026-09-30 10:42:03 +00:00

test_per_token_kv_cache.py

[CI] Ignore ruff D209, rejoin the docstrings it split, and silence incompatible-rule warnings (#57212)

2026-09-16 10:57:24 -07:00

test_quantization_config_args.py

[Quantization] Support online quantization with partially pre-quantized checkpoints (#51392)

2026-09-04 11:46:06 -07:00

test_quark.py

[Bugfix][ROCm] AMD-Quark mixed-precision DeepSeek-V4.1 support (#57071)

2026-09-25 20:51:18 -05:00

test_register_quantization_config.py

Add pydocstyle to the ruff rules (#52136)

2026-09-16 16:44:29 +00:00

test_rocm_moe.py

[ROCm][CI] Add quantized MoE serving test for gfx950 (#58748)

2026-09-25 18:02:15 +00:00

test_torchao.py

[Tests] Delete deprecate torchao tests for v1 configs (#52956)

2026-09-16 23:11:27 +00:00

test_trtllm_nvfp4_hidden_dim_padding.py

[Quantization] Add per-token NVFP4 CuTe-DSL MoE backend (#50030)

2026-09-30 10:42:03 +00:00

test_turboquant.py

[6/N][KV-Cache Layout Refactor] Standardize KV cache layout (#51718)

2026-08-21 17:47:49 -07:00

utils.py

[CI] Speed up quantization test group (#53291)

2026-09-01 13:15:24 -05:00