3 people ec59c1579f [MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120) ...

Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

2026-07-21 19:20:30 -07:00

..

compressed_tensors

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

inc

[Quantization][INC][ARK] Support INT2 XPU WOQ Linear (#47521)

2026-07-14 08:29:45 +08:00

online

[Quant] Add nvfp4_per_token online MoE quantization (#48538)

2026-07-16 14:25:27 -07:00

quark

[ROCm][Bugfix] Fix GPT-OSS Quark MXFP4 MoE loading - emulation buffer not block-aligned (#43979)

2026-07-18 03:49:41 +00:00

turboquant

…

utils

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

__init__.py

[Quant] Add nvfp4_per_token online MoE quantization (#48538)

2026-07-16 14:25:27 -07:00

auto_awq.py

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

auto_gptq.py

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

awq_triton.py

…

base_config.py

…

bitsandbytes.py

…

experts_int8.py

…

fbgemm_fp8.py

…

fp8.py

…

fp_quant.py

…

humming.py

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

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

input_quant_fp8.py

…

kv_cache.py

[Model][Hardware][AMD]: Part 1/2 -> Enable e2e QK Norm + RoPE + KV Cache runtime fusion for Qwen3-30B-A3B on ROCM_AITER_FA, and ROCM_AITER_UNIFIED_ATTN (#42749)

2026-07-16 17:39:04 -05:00

modelopt.py

[BugFix] Fix ModelOpt mixed-precision quantization for sparse quantized_layers configs. (#47318)

2026-07-07 11:45:13 +00:00

moe_wna16.py

[MoE Refactor] Migrate MoeWNA16Method quantization method over to using the new MK oracle scheme. (#44120)

2026-07-21 19:20:30 -07:00

mxfp4.py

…

qutlass_utils.py

…

torchao.py

…