Mingyuan Ma b4c8fbaae2

Add TRTLLM MoE NVFP4 kernel to CompressedTensorsW4A4MoeMethod (#28892) ...

Signed-off-by: mingyuanm <mingyuanm@nvidia.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>

2025-11-21 09:54:11 -07:00

..

compressed_tensors

Add TRTLLM MoE NVFP4 kernel to CompressedTensorsW4A4MoeMethod (#28892)

2025-11-21 09:54:11 -07:00

kernels

[ROCM] Fix ROCm warnings, environment flag access, and GEMM kernel naming for consistency in _aiter_ops.py (#28464)

2025-11-12 21:46:57 +00:00

quark

Upstream triton fp4 weight preshuffle (#28888)

2025-11-21 11:34:46 -05:00

utils

Add TRTLLM MoE NVFP4 kernel to CompressedTensorsW4A4MoeMethod (#28892)

2025-11-21 09:54:11 -07:00

__init__.py

[CPU] Refactor CPU WNA16 (#28826)

2025-11-19 10:32:00 +08:00

auto_round.py

…

awq_marlin.py

[Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410)

2025-11-11 23:16:12 +00:00

awq_triton.py

…

awq.py

…

base_config.py

…

bitblas.py

…

bitsandbytes.py

[Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123)

2025-11-04 21:59:45 +08:00

cpu_wna16.py

[CPU] Refactor CPU WNA16 (#28826)

2025-11-19 10:32:00 +08:00

deepspeedfp.py

…

experts_int8.py

[Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123)

2025-11-04 21:59:45 +08:00

fbgemm_fp8.py

…

fp8.py

[Log] Optimize startup log (#28948)

2025-11-21 08:46:20 -08:00

fp_quant.py

…

gguf.py

[Model] Add Gemma3 GGUF multimodal support (#27772)

2025-11-18 08:56:29 -08:00

gptq_bitblas.py

…

gptq_marlin_24.py

…

gptq_marlin.py

[Bugfix] Disable shared expert overlap if Marlin MoE is used (#28410)

2025-11-11 23:16:12 +00:00

gptq.py

…

hqq_marlin.py

…

inc.py

…

input_quant_fp8.py

…

ipex_quant.py

[CPU] Refactor CPU WNA16 (#28826)

2025-11-19 10:32:00 +08:00

kv_cache.py

…

modelopt.py

Add TRTLLM MoE NVFP4 kernel to CompressedTensorsW4A4MoeMethod (#28892)

2025-11-21 09:54:11 -07:00

moe_wna16.py

[Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123)

2025-11-04 21:59:45 +08:00

mxfp4.py

[Bugfix] Fix FusedMoEModularKernel for triton backend (#28913)

2025-11-19 13:05:22 +08:00

petit.py

…

ptpc_fp8.py

…

qutlass_utils.py

…

rtn.py

[Kernels] Isolate modular kernel code from FusedMoEMethodBase subclasses. (#27123)

2025-11-04 21:59:45 +08:00

schema.py

…

torchao.py

Support using Int4PreshuffledTensor after loading (#26066)

2025-11-04 06:00:57 -05:00

tpu_int8.py

…