[inference] Add smmoothquant for llama (#4904)

* [inference] add int8 rotary embedding kernel for smoothquant (#4843)

* [inference] add smoothquant llama attention (#4850)

* add smoothquant llama attention

* remove uselss code

* remove useless code

* fix import error

* rename file name

* [inference] add silu linear fusion for smoothquant llama mlp  (#4853)

* add silu linear

* update skip condition

* catch smoothquant cuda lib exception

* prcocess exception for tests

* [inference] add llama mlp for smoothquant (#4854)

* add llama mlp for smoothquant

* fix down out scale

* remove duplicate lines

* add llama mlp check

* delete useless code

* [inference] add smoothquant llama (#4861)

* add smoothquant llama

* fix attention accuracy

* fix accuracy

* add kv cache and save pretrained

* refactor example

* delete smooth

* refactor code

* [inference] add smooth function and delete useless code for smoothquant (#4895)

* add smooth function and delete useless code

* update datasets

* remove duplicate import

* delete useless file

* refactor codes (#4902)

* rafactor code

* add license

* add torch-int and smoothquant license

colossalai/kernel/triton/__init__.py

@@ -13,8 +13,10 @@ if HAS_TRITON:
     from .copy_kv_cache_dest import copy_kv_cache_to_dest
     from .fused_layernorm import layer_norm
     from .gptq_triton import gptq_fused_linear_triton
+    from .int8_rotary_embedding_kernel import int8_rotary_embedding_fwd
     from .rms_norm import rmsnorm_forward
     from .rotary_embedding_kernel import rotary_embedding_fwd
+    from .smooth_attention import smooth_llama_context_attn_fwd, smooth_token_attention_fwd
     from .softmax import softmax
     from .token_attention_kernel import token_attention_fwd
 
@@ -29,4 +31,7 @@ if HAS_TRITON:
         "rotary_embedding_fwd",
         "token_attention_fwd",
         "gptq_fused_linear_triton",
+        "int8_rotary_embedding_fwd",
+        "smooth_llama_context_attn_fwd",
+        "smooth_token_attention_fwd",
     ]