Stefano CastagnettaandKartikey Vyas 4e0681ed56 [Quantization] Support packed NVFP4 Qwen4Exp PLE embeddings (#56273) ...

Signed-off-by: Stefano Castagnetta <scastagnetta@nvidia.com>
Co-authored-by: Kartikey Vyas <kartikey@artificialanalysis.ai>

2026-10-14 08:24:55 +08:00

..

compressed_tensors

[Bugfix] Keep compressed-tensors wNa16 linear layers batch invariant (#60524)

2026-10-13 15:43:40 -04:00

inc

[feat] FlashInfer CuteDSL MegaMoE integration (#54049)

2026-10-02 15:43:33 -04:00

online

[Feature] Support batch invariance on ROCm (#52231)

2026-10-12 10:53:26 -05:00

quark

[Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)

2026-10-02 15:50:38 +00:00

turboquant

Add pydocstyle to the ruff rules (#52136)

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

utils

[Quantization] Support packed NVFP4 Qwen4Exp PLE embeddings (#56273)

2026-10-14 08:24:55 +08:00

__init__.py

Add pydocstyle to the ruff rules (#52136)

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

auto_awq.py

[Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)

2026-10-02 15:50:38 +00:00

auto_gptq.py

[Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)

2026-10-02 15:50:38 +00:00

awq_triton.py

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

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

base_config.py

[Quantization] Enable shared expert fusion compatibility with online shared_expert quantization (showcase: along Quark MXFP4 routed experts) (#55686)

2026-10-08 12:04:46 -04:00

experts_int8.py

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

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

fbgemm_fp8.py

[ROCm][FEAT] Integrate aiter gemm w8a8 ptpc (#33773)

2026-04-16 09:55:29 +08:00

fp8.py

[Feature] Support batch invariance on ROCm (#52231)

2026-10-12 10:53:26 -05:00

fp_quant.py

Add pydocstyle to the ruff rules (#52136)

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

humming.py

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

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

input_quant_fp8.py

[Perf] Use value-only reduction for native per-token FP8 quantization (#59800)

2026-10-02 18:37:17 +00:00

kv_cache.py

Add pydocstyle to the ruff rules (#52136)

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

modelopt_block_quant.py

[Quantization] Add ModelOpt IQ2_XS, IQ2_XXS, and Q8_0 support via b12x (#59604)

2026-10-13 09:06:33 -07:00

modelopt.py

[Quantization] Add ModelOpt IQ2_XS, IQ2_XXS, and Q8_0 support via b12x (#59604)

2026-10-13 09:06:33 -07:00

moe_wna16.py

[Bugfix] Bind routed-experts capture to the MoE layer, not the kernel (#59455)

2026-10-02 15:50:38 +00:00

mxfp4.py

[ROCm][Kimi-K3] Add opt-in gfx942 MXFP4-to-int4 conversion (#51274)

2026-10-03 14:28:02 +08:00

qutlass_utils.py

Add pydocstyle to the ruff rules (#52136)

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

torchao.py

Add pydocstyle to the ruff rules (#52136)

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