yuehuayingxueluo
|
249644c23b
|
[Inference]Repalce Attention layer and MLP layer by shardformer to optimize the weight transpose operation，add fused_qkv and fused linear_add (#5340)
* add fused qkv
* replace attn and mlp by shardformer
* fix bugs in mlp
* add docstrings
* fix test_inference_engine.py
* add optimize unbind
* add fused_addmm
* rm squeeze(1)
* refactor codes
* fix ci bugs
* rename ShardFormerLlamaMLP and ShardFormerLlamaAttention
* Removed the dependency on LlamaFlashAttention2
* rollback test_inference_engine.py
|
2024-02-01 15:49:39 +08:00 |
|
Yuanheng Zhao
|
5f98a9d68a
|
[Infer] Optimize Blocked KVCache And Kernels Using It (#5325)
* revise shape of kvcache (context attn kernel)
* revise shape of kvcache (flash decoding kernel)
* revise shape of kvcache (kvcache copy) and attn func
* init of kvcache in kvcache manager
* revise llama modeling
* revise block size retrieval
* use torch for rms_norm benchmarking
* revise block size retrieval
|
2024-01-30 16:06:09 +08:00 |
|
yuehuayingxueluo
|
4f28cb43c0
|
[inference]Optimize the usage of the mid tensors space in flash attn (#5304)
* opt flash attn
* opt tmp tensor
* fix benchmark_llama
* fix code style
* fix None logic for output tensor
* fix adapted to get_xine_cache
* add comment
* fix ci bugs
* fix some codes
* rm duplicated codes
* rm duplicated codes
* fix code style
* add _get_dtype in config.py
|
2024-01-26 14:00:10 +08:00 |
|
Yuanheng Zhao
|
3da9993b0d
|
[Kernel/Fix] Revise flash attention triton kernel API and add benchmark (#5301)
* fix decoding kernel pytest
* revise and add triton context attn benchmark
|
2024-01-23 17:16:02 +08:00 |
|
Yuanheng Zhao
|
6e487e7d3c
|
[kernel/fix] Performance Optimization for Decoding Kernel and Benchmarking (#5274)
* prevent re-creating intermediate tensors
* add singleton class holding intermediate values
* fix triton kernel api
* add benchmark in pytest
* fix kernel api and add benchmark
* revise flash decoding triton kernel in/out shapes
* fix calling of triton kernel in modeling
* fix pytest: extract to util functions
|
2024-01-19 15:47:16 +08:00 |
|
Yuanheng Zhao
|
1513f20f4d
|
[kernel] Add flash decoding triton kernel for blocked kv cache (#5249)
* add flash decoding unpad triton kernel
* rename flash decoding kernel
* add kernel testing (draft)
* revise pytest
* support kv group (GQA)
* (trivial) fix api and pytest
* (trivial) func renaming
* (trivial) func/file renaming
* refactor pytest for attention
* (trivial) format and consistent vars of context/decode attn
* (trivial) remove test redundancy
|
2024-01-11 13:46:14 +00:00 |