chenqianfzh 4664ceaad6 support bitsandbytes 8-bit and FP4 quantized models (#7445)		2024-08-29 19:09:08 -04:00
..
__init__.py	[CI/Build] Move test_utils.py to tests/utils.py (#4425)	2024-05-13 23:50:09 +09:00
test_bitsandbytes.py	support bitsandbytes 8-bit and FP4 quantized models (#7445)	2024-08-29 19:09:08 -04:00
test_compressed_tensors.py	[Kernel] Expand MoE weight loading + Add Fused Marlin MoE Kernel (#7766)	2024-08-27 15:07:09 -07:00
test_configs.py	[Kernel][Core] Add AWQ support to the Marlin kernel (#6612)	2024-07-21 19:41:42 -04:00
test_cpu_offload.py	[ci][test] adjust max wait time for cpu offloading test (#7709)	2024-08-20 17:12:44 -07:00
test_experts_int8.py	[Kernel] W8A16 Int8 inside FusedMoE (#7415)	2024-08-16 10:06:51 -07:00
test_fp8.py	[Misc/Testing] Use torch.testing.assert_close (#7324)	2024-08-16 04:24:04 +00:00
test_lm_head.py	[Core] Support loading GGUF model (#5191)	2024-08-05 17:54:23 -06:00
utils.py	[hardware][misc] introduce platform abstraction (#6080)	2024-07-02 20:12:22 -07:00