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.
ColossalAI/tests/test_infer_ops/triton
Cuiqing Li bce0f16702
[Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577)
1 year ago
..
kernel_utils.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_bloom_context_attention.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_copy_kv_dest.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_layernorm_triton.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_llama_context_attention.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_rotary_embedding.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_self_attention_nonfusion.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_softmax.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_token_attn_1.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_token_attn_2.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_token_attn_fwd.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago
test_token_softmax.py [Feature] The first PR to Add TP inference engine, kv-cache manager and related kernels for our inference system (#4577) 1 year ago