Michael Goin 03b91f7262

[Bugfix] Fix compressed-tensors models failing to load with transformers backend (#30287) ...

Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>

2025-12-08 20:44:28 -08:00

..

compressed_tensors

[Bugfix] Fix compressed-tensors models failing to load with transformers backend (#30287)

2025-12-08 20:44:28 -08:00

kernels

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

quark

[ROCm] [Fused Moe EP] Use binary expert mask for aiter fused moe kernel (#29773)

2025-12-08 05:23:46 +00:00

utils

[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691)

2025-12-08 19:29:06 -08:00

__init__.py

[CPU] Refactor CPU WNA16 (#28826)

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

auto_round.py

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

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

awq_marlin.py

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

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

awq_triton.py

…

awq.py

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

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

base_config.py

…

bitblas.py

…

bitsandbytes.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

cpu_wna16.py

[CPU] Refactor CPU WNA16 (#28826)

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

deepspeedfp.py

…

experts_int8.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

fbgemm_fp8.py

…

fp8.py

online fp8 quant with streaming weight post-processing (#29196)

2025-12-08 20:15:10 +00:00

fp_quant.py

…

gguf.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

gptq_bitblas.py

…

gptq_marlin_24.py

…

gptq_marlin.py

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

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

gptq.py

…

hqq_marlin.py

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

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

inc.py

…

input_quant_fp8.py

…

ipex_quant.py

[XPU] Fix AWQ skipped layer detection in IPEX quantization (#29774)

2025-12-01 12:00:52 +00:00

kv_cache.py

…

modelopt.py

[Feat] Support non-gated activations in NVFP4 modelopt path (#29004)

2025-11-30 11:02:40 -05:00

moe_wna16.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

mxfp4.py

[LoRA] Support FusedMoE LoRA Triton kernel for mxfp4 (#29708)

2025-11-30 10:37:25 +08:00

petit.py

[Attention] Update attention imports (#29540)

2025-11-27 11:19:09 -05:00

ptpc_fp8.py

[Attention] Update attention imports (#29540)

2025-11-27 11:19:09 -05:00

qutlass_utils.py

…

rtn.py

[MoE][Refactor] Make select_experts a non-static method (#29067)

2025-11-24 13:38:04 -05:00

schema.py

…

torchao.py

Support using Int4PreshuffledTensor after loading (#26066)

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

tpu_int8.py

…