Dipika Sikka cd3edfc908 [Misc] Add compressed-tensors NVFP4A16 emulation support (#17914) ...

Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>

2025-05-11 15:58:38 +08:00

..

__init__.py

…

test_bitsandbytes.py

[Misc] Auto detect bitsandbytes pre-quantized models (#16027)

2025-04-04 23:30:45 -07:00

test_compressed_tensors.py

[Misc] Add compressed-tensors NVFP4A16 emulation support (#17914)

2025-05-11 15:58:38 +08:00

test_configs.py

…

test_cpu_offload.py

[V1] Fully Transparent Implementation of CPU Offloading (#15354)

2025-03-31 20:22:34 +08:00

test_experts_int8.py

…

test_fp8.py

…

test_gptq_dynamic.py

…

test_ipex_quant.py

…

test_lm_head.py

…

test_ptpc_fp8.py

…

test_quark.py

[Bugfix] Fix quark fp8 format loading on AMD GPUs (#12612)

2025-05-08 02:53:53 -07:00

test_register_quantization_config.py

Improve configs - ModelConfig (#17130)

2025-04-30 10:38:22 +08:00

test_torchao.py

Add pt_load_map_location to allow loading to cuda (#16869)

2025-05-01 23:23:42 -07:00

utils.py

…