main
ColossalAI
Repository badge with A rating
View on GitHub
Grade
Name
Complexity
Churn
Issues
A
examples\inference\stable_diffusion\compute_metric.py
12 1 -
A
examples\inference\llama\run_benchmark.sh
 1 -
A
extensions\csrc\kernel\cuda\decode_kv_cache_memcpy_kernel.cu
 1 -
A
applications\Colossal-LLaMA\colossal_llama\dataset\dummy_dataset.py
3 1 -
A
colossalai\kernel\triton\rms_layernorm.py
10 1 -
A
colossalai\booster\mixed_precision\fp8.py
 1 -
A
examples\inference\benchmark_ops\benchmark_rotary_embedding.py
5 1 -
A
colossalai\kernel\triton\context_attn_unpad.py
26 1 -
A
examples\inference\benchmark_ops\benchmark_kv_cache_memcopy.py
7 1 -
A
colossalai\kernel\triton\no_pad_rotary_embedding.py
15 1 -
A
examples\inference\benchmark_ops\benchmark_xine_copy.py
3 1 -
A
tests\test_infer\test_kernels\cuda\test_convert_fp8.py
1 1 -
A
tests\test_infer\test_inference_engine.py
 1 -
A
docs\conda-doc-test-deps.yml
 1 -
A
colossalai\legacy\moe\openmoe\model\modeling_openmoe.py
136 1 -
A
colossalai\legacy\moe\manager.py
18 1 -
A
colossalai\legacy\inference\tensor_parallel\modeling\bloom.py
59 1 -
A
colossalai\legacy\inference\tensor_parallel\__init__.py
 1 -
A
colossalai\legacy\inference\serving\ray_serve\send_request.py
1 1 -
A
colossalai\inference\modeling\backends\pre_attention_backend.py
18 1 -