Kunshang Ji 36dcaf25d8 [XPU] add gptq(int4) support (#37844) ...

Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>

2026-05-19 11:17:09 +08:00

..

compressed_tensors

[Refactor] Remove dead code (#42889)

2026-05-18 16:41:22 -04:00

online

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 15:43:13 -07:00

quark

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

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

turboquant

[Refactor] Remove dead code (#42889)

2026-05-18 16:41:22 -04:00

utils

[XPU] add gptq(int4) support (#37844)

2026-05-19 11:17:09 +08:00

__init__.py

[Model Refactoring] Migrate DeepSeek V4 to vllm/models/ [1/N] (#43004)

2026-05-18 19:50:02 -07:00

auto_gptq.py

Refactor AWQ Marlin MoE onto modular WNA16 oracle (#42483)

2026-05-18 08:02:43 -07:00

awq_marlin.py

Refactor AWQ Marlin MoE onto modular WNA16 oracle (#42483)

2026-05-18 08:02:43 -07:00

awq_triton.py

…

awq.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

base_config.py

…

bitsandbytes.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

cpu_wna16.py

[CPU] Bump up to the latest CPU kernels (#41924)

2026-05-07 05:45:59 -07:00

experts_int8.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

fbgemm_fp8.py

…

fp8.py

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 15:43:13 -07:00

fp_quant.py

…

gguf.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

humming.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

inc.py

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

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

input_quant_fp8.py

…

kv_cache.py

…

modelopt.py

[Bugfix] Add swiglu limits to deepgemm fp8 methods (#41986)

2026-05-14 15:43:13 -07:00

moe_wna16.py

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

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

mxfp4.py

[MoE Refactor] Introduce RoutedExperts alias for FusedMoE and don't store SharedExperts in MK (#40735)

2026-05-12 13:37:44 -04:00

qutlass_utils.py

…

torchao.py

…