Making large AI models cheaper, faster and more accessible
You can not select more than 25 topics Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
 
 
 
 
 
Steve Luo 7806842f2d
add paged-attetionv2: support seq length split across thread block (#5707)
6 months ago
..
benchmark_context_attn_unpad.py [Fix] Fix & Update Inference Tests (compatibility w/ main) 7 months ago
benchmark_decoding_attn.py [Fix] Fix & Update Inference Tests (compatibility w/ main) 7 months ago
benchmark_flash_decoding_attention.py add paged-attetionv2: support seq length split across thread block (#5707) 6 months ago
benchmark_fused_rotary_embdding_unpad.py [Fix] Fix & Update Inference Tests (compatibility w/ main) 7 months ago
benchmark_kv_cache_memcopy.py [Fix] Fix & Update Inference Tests (compatibility w/ main) 7 months ago
benchmark_rmsnorm.py feat baichuan2 rmsnorm whose hidden size equals to 5120 (#5611) 7 months ago
benchmark_rotary_embedding.py [Inference/kernel]Add Fused Rotary Embedding and KVCache Memcopy CUDA Kernel (#5418) 8 months ago
benchmark_xine_copy.py [Fix] Fix & Update Inference Tests (compatibility w/ main) 7 months ago
test_ci.sh [Fix] Fix Inference Example, Tests, and Requirements (#5688) 7 months ago