Steve Luo a8fd3b0342 [Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643) ... * optimize flashdecodingattention: refactor code with different key cache layout(from [num_blocks, num_kv_heads, block_size, head_size] to [num_blocks, num_kv_heads, head_size/x, block_size, x]) * [pre-commit.ci] auto fixes from pre-commit.com hooks for more information, see https://pre-commit.ci --------- Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>		2024-04-25 14:24:02 +08:00
..
test_models	[inference/model]Adapted to the baichuan2-7B model (#5591)	2024-04-15 16:53:02 +08:00
test_ops	[Inference/Kernel] Optimize paged attention: Refactor key cache layout (#5643)	2024-04-25 14:24:02 +08:00
_utils.py	[Inference] Add the logic of the inference engine (#5173)	2024-01-11 13:39:56 +00:00
test_batch_bucket.py	[Fix/Inference] Fix format of input prompts and input model in inference engine (#5395)	2024-02-23 10:51:35 +08:00
test_config_and_struct.py	[Inference] Optimize and Refactor Inference Batching/Scheduling (#5367)	2024-02-19 17:18:20 +08:00
test_cuda_graph.py	[Feat]Tensor Model Parallel Support For Inference (#5563)	2024-04-18 16:56:46 +08:00
test_drafter.py	[Inference/SpecDec] Support GLIDE Drafter Model (#5455)	2024-04-10 11:07:52 +08:00
test_inference_engine.py	[Fix/Inference] Fix GQA Triton and Support Llama3 (#5624)	2024-04-23 13:09:55 +08:00
test_kvcache_manager.py	[Inference] Optimize and Refactor Inference Batching/Scheduling (#5367)	2024-02-19 17:18:20 +08:00
test_request_handler.py	[Inference] Optimize and Refactor Inference Batching/Scheduling (#5367)	2024-02-19 17:18:20 +08:00