RICHARDNAN 3a966d6fb1 Merge branch 'csx-main-fix' into csx-main-fix		2025-10-23 17:55:03 +08:00
..
ascend	处理检视意见	2025-10-23 11:28:42 +08:00
__init__.py	Initial commit	2024-07-27 16:06:58 +08:00
attention.py	add XPU support for qwen3moe local chat	2025-05-22 21:01:41 +08:00
balance_serve_attention.py	fix bug	2025-09-16 13:21:58 +00:00
base_operator.py	support safetensor load, delete architectures argument	2025-05-09 10:38:29 +00:00
cpuinfer.py	cpuinfer: filter repeated backend instantiation	2025-03-10 22:03:04 +08:00
dynamic_attention.py	merge main; Add torch q8 linear	2025-03-14 05:52:07 -04:00
experts.py	fix: 合并最新main, 解决冲突	2025-09-29 17:30:40 +08:00
flashinfer_batch_prefill_wrapper.py	fix:修复balance_server tp=1 不开图下沉报错	2025-09-22 20:52:07 +08:00
flashinfer_wrapper.py	fix:修复balance_server tp=1 不开图下沉报错	2025-09-22 20:52:07 +08:00
gate.py	fix:修复balance_server tp=1 不开图下沉报错	2025-09-22 20:52:07 +08:00
layernorm.py	support qwen3 next	2025-09-11 09:56:21 +00:00
linear.py	fix:修复balance_server tp=1 不开图下沉报错	2025-09-22 20:52:07 +08:00
mlp.py	support smt and qlm4	2025-07-25 12:48:51 +00:00
models.py	fix transformers local_chat	2025-10-23 17:51:19 +08:00
RoPE.py	support smt and qlm4	2025-07-25 12:48:51 +00:00
triton_attention.py	merge main; Add torch q8 linear	2025-03-14 05:52:07 -04:00
triton_attention_prefill.py	merge main; Add torch q8 linear	2025-03-14 05:52:07 -04:00