3 people 385ba6b5b0 [Bugfix][Quantization] Register Quark per-block FP8 scales as weight_scale (#54770) ...

Signed-off-by: jimmy-adams <41593649+jimmy-adams@users.noreply.github.com>
Co-authored-by: fxmarty-amd <felmarty@amd.com>
Co-authored-by: Shanshan Shen <467638484@qq.com>

2026-09-05 10:44:24 +08:00

..

configs

[AMD][QWEN3-NEXT] FP8 Tunings (#32042)

2026-01-27 09:34:13 +00:00

__init__.py

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

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

allspark_utils.py

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

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

b12x_moe.py

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

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

config_utils.py

[Online quantization] Add targeted online quantization configuration based on user patterns (#51285)

2026-09-02 08:55:15 -04:00

flashinfer_fp4_moe.py

feat: extended EPLB support for Mistral Large 3 and additional MoE backends (#48355)

2026-08-07 05:32:52 -07:00

flashinfer_mxint4_moe.py

Revert "[Bugfix][MoE] Tune FlashInfer experts to scheduler token limit" (#52989) (#53186)

2026-08-21 12:39:28 -06:00

flashinfer_utils.py

[Model] add GLM-5.3-Flash support (#53906)

2026-09-03 09:40:35 -07:00

fp8_utils.py

[Bugfix][Quantization] Register Quark per-block FP8 scales as weight_scale (#54770)

2026-09-05 10:44:24 +08:00

gptq_utils.py

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

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

humming_utils.py

[Quantization][Humming] Support MXFP4 weight + block-FP8 activation for MoE (#51332)

2026-08-25 10:21:00 -04:00

int8_utils.py

[Refactor] Remove dead code for quantization (#52221)

2026-08-16 13:10:16 -04:00

layer_utils.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

machete_utils.py

[Refactor] Remove multiple dead code (#47329)

2026-07-06 07:54:08 -07:00

marlin_utils_fp4.py

[Bugfix] Preserve Marlin runtime tensor storage across weight reload (#48438)

2026-07-30 14:50:03 -07:00

marlin_utils_fp8.py

[Bugfix] Preserve Marlin runtime tensor storage across weight reload (#48438)

2026-07-30 14:50:03 -07:00

marlin_utils_test.py

[Kernel][Quantization] add w4a8 support for marlin kernel (#24722)

2025-11-29 07:19:33 -08:00

marlin_utils.py

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

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

mxfp4_utils.py

[Refactor] Remove dead code for quantization (#52221)

2026-08-16 13:10:16 -04:00

mxfp6_utils.py

[Chore] Clean up pytorch helper functions in vllm.utils (#26908)

2025-10-18 09:48:22 -07:00

mxfp8_utils.py

[Bugfix][ROCM] Fix the MXFP8 block scale exponent (#53110)

2026-08-22 01:26:19 +00:00

nvfp4_emulation_utils.py

[ROCm][CI] Extended Fused MoE and FP8 MoE test support (#41100)

2026-08-19 10:19:42 -05:00

nvfp4_utils.py

[Refactor] Move NVFP4 GEMM management into NvFp4LinearKernel (#39129)

2026-04-09 15:05:36 -04:00

ocp_mx_utils.py

[Quantization][Refactor][1/N] Adopt QuantKey in QuarkConfig and methods, relying on weight_quant_key, act_quant_key for quant method dispatch (#52958)

2026-09-01 02:55:54 -05:00

quant_utils.py

[Quantization][Refactor][1/N] Adopt QuantKey in QuarkConfig and methods, relying on weight_quant_key, act_quant_key for quant method dispatch (#52958)

2026-09-01 02:55:54 -05:00

w8a8_utils.py

[Refactor] Remove dead code quantization 2 (#52821)

2026-08-25 20:28:44 -07:00