Juhi Mittal e203006a8b [Quantization][ModelOpt] W4A16 NVFP4 fused MoE + mixed-precision dispatch (#42566) ...

Signed-off-by: Juhi Mittal <juhim@nvidia.com>

2026-05-22 20:51:49 +00:00

..

__init__.py

…

fp_quant.py

…

reference_mxfp4.py

…

test_auto_gptq.py

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

test_auto_round.py

…

test_blackwell_moe.py

[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

test_compressed_tensors.py

Remove additional dead code as a follow-up to #42889 (#43144)

2026-05-20 10:01:45 -04:00

test_configs.py

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

test_cpu_offload.py

[CI] Stabilize cpu offload compressed tensors test (#41102)

2026-05-04 05:22:42 +00:00

test_cpu_wna16.py

[CPU] Add MXFP4 W4A16 MoE support (#41922)

2026-05-18 03:04:45 -07:00

test_cutlass_w4a16.py

[AMD] skip machete tests for rocm (#42326)

2026-05-13 12:11:03 +00:00

test_experts_int8.py

…

test_fp8.py

[Bug] Fix ci issue assert output_size is not None AssertionError (#43261)

2026-05-21 16:58:09 +08:00

test_gfx950_moe.py

[ROCm][Quantization][3/N] Refactor quark_moe w4a4 w/ oracle (#41436)

2026-05-18 13:46:13 -04:00

test_gptq_dynamic.py

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

test_gptq_v2.py

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

test_lm_head.py

[Quant] Consolidate GPTQ: rename gptq_marlin.py to auto_gptq.py (#38288)

2026-05-15 08:25:52 +08:00

test_mixed_precision.py

…

test_modelopt.py

[Quantization][ModelOpt] W4A16 NVFP4 fused MoE + mixed-precision dispatch (#42566)

2026-05-22 20:51:49 +00:00

test_online.py

[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

test_per_token_kv_cache.py

…

test_quantization_config_args.py

[Quantization] Rework quantization_config to use QuantKey and allow for activation override (#41566)

2026-05-13 16:58:32 -04:00

test_quark.py

[Quark] Support loading Quark NVFP4 checkpoints in vLLM (#35859)

2026-05-13 11:17:36 -07:00

test_register_quantization_config.py

…

test_torchao.py

…

test_trtllm_nvfp4_hidden_dim_padding.py

…

test_turboquant.py

[Feature] TurboQuant: support hybrid models and uniform quantization (#39931)

2026-05-04 20:14:01 -04:00

utils.py

…