danisereb 084aa19f02 Add support for ModelOpt MXFP8 dense models (#33786) ...

Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>

2026-02-08 11:16:48 -08:00

..

compressed_tensors

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

kernels

[XPU][5/N] add wna16 xpu kernel (#33973)

2026-02-06 15:59:53 +00:00

quark

[Rocm][Bugfix] Fix dtype not same for gemm_a4w4 op (#33734)

2026-02-06 19:09:59 +00:00

utils

Add support for ModelOpt MXFP8 dense models (#33786)

2026-02-08 11:16:48 -08:00

__init__.py

Add support for ModelOpt MXFP8 dense models (#33786)

2026-02-08 11:16:48 -08:00

awq_marlin.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

awq_triton.py

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

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

awq.py

[Bugfix] Fix missing is_layer_skipped check for FusedMoE in AWQConfig (#32935)

2026-01-23 17:19:56 -05:00

base_config.py

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

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

bitsandbytes.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

cpu_wna16.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

experts_int8.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

fbgemm_fp8.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

fp8.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

fp_quant.py

"refactor: refactor_repeated_interfaces" (#32486)

2026-01-18 22:07:01 +08:00

gguf.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

gptq_marlin.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

gptq.py

[Quantization][Deprecation] Remove BitBlas (#32683)

2026-01-28 11:06:22 +00:00

inc.py

[XPU][1/N] Deprecate ipex and switch to vllm-xpu-kernels for xpu platform (#33379)

2026-02-02 22:46:10 -08:00

input_quant_fp8.py

[W8A8 Block Linear Refactor][1/N] Keep all quantization types into QuantFP8 class. (#33047)

2026-02-01 09:28:01 +00:00

kv_cache.py

[Bugfix][Attention] Explicitly report support for kv_cache_dtype bfloat16 (#32795)

2026-01-22 19:05:18 +00:00

modelopt.py

Add support for ModelOpt MXFP8 dense models (#33786)

2026-02-08 11:16:48 -08:00

moe_wna16.py

[Moe Refactor] Make Inplace Flag for FusedMoEModularKernel part of the constructor (#33375)

2026-02-05 18:07:18 +00:00

mxfp4.py

[XPU][4/N] add mxfp4 moe model support (#33679)

2026-02-06 13:03:59 +08:00

petit.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

ptpc_fp8.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00

qutlass_utils.py

"refactor: refactor_repeated_interfaces" (#32486)

2026-01-18 22:07:01 +08:00

schema.py

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

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

torchao.py

[Misc] Replace Optional[X] with X | None syntax (#33332)

2026-01-30 01:56:59 -08:00