llm.c-0e69e3a
File List
- train_gpt2.cu 87.4 KB
- train_gpt2_fp32.cu 75.3 KB
- dev/cuda/layernorm_backward.cu 70.3 KB
- dev/cuda/attention_forward.cu 53.4 KB
- train_gpt2.c 49.5 KB
- dev/cuda/attention_backward.cu 48.0 KB
- train_gpt2.py 41.1 KB
- dev/cuda/classifier_fused.cu 35.6 KB
- dev/cuda/fused_residual_forward.cu 27.3 KB
- dev/cuda/trimat_forward.cu 26.8 KB
- dev/cuda/matmul_backward_bias.cu 26.5 KB
- dev/cuda/softmax_forward.cu 24.5 KB
- llmc/dataloader.h 21.0 KB
- dev/cuda/layernorm_forward.cu 19.6 KB
- llmc/layernorm.cuh 18.7 KB
- doc/layernorm/layernorm.md 18.0 KB
- dev/cuda/matmul_forward.cu 17.8 KB
- test_gpt2.cu 14.7 KB
- README.md 13.3 KB
- llmc/attention.cuh 13.0 KB
- llmc/cudnn_att.cpp 12.4 KB
- dev/cuda/common.h 12.1 KB
- test_gpt2_fp32.cu 10.8 KB
- dev/cuda/matmul_backward.cu 10.7 KB
- llmc/encoder.cuh 10.5 KB
- Makefile 10.0 KB
- dev/cuda/adamw.cu 9.5 KB
- llmc/matmul.cuh 9.5 KB
- llmc/zero.cuh 8.9 KB
- profile_gpt2cu.py 8.5 KB
- dev/cuda/encoder_forward.cu 8.4 KB
- llmc/cuda_utils.cuh 8.2 KB
- test_gpt2.c 7.8 KB
- dev/data/hellaswag.py 7.5 KB
- dev/cuda/nccl_all_reduce.cu 7.4 KB
- dev/cpu/matmul_forward.c 7.0 KB
- llmc/rand.h 6.8 KB
- dev/cuda/global_norm.cu 6.7 KB
- dev/cuda/gelu_backward.cu 6.7 KB
- dev/cuda/encoder_backward.cu 6.5 KB
- llmc/mfu.h 6.1 KB
- llmc/fused_classifier.cuh 6.1 KB
- doc/layernorm/layernorm.c 6.1 KB
- dev/cuda/crossentropy_softmax_backward.cu 5.9 KB
- dev/data/mmlu.py 5.7 KB
- dev/cuda/benchmark_on_modal.py 5.6 KB
- dev/cuda/gelu_forward.cu 5.5 KB
- dev/cuda/residual_forward.cu 5.3 KB
- llmc/utils.h 5.2 KB
- dev/cuda/crossentropy_forward.cu 4.9 KB
- dev/unistd.h 4.7 KB
- dev/data/data_common.py 4.5 KB
- llmc/adamw.cuh 4.4 KB
- dev/vislog.ipynb 4.3 KB
- dev/data/fineweb.py 4.3 KB
- dev/data/tinystories.py 4.0 KB
- llmc/tokenizer.h 3.6 KB
- llmc/cuda_common.h 3.5 KB
- scripts/README.md 2.7 KB
- llmc/gelu.cuh 2.6 KB
- llmc/global_norm.cuh 2.5 KB
- dev/cuda/Makefile 2.4 KB
- dev/cuda/README.md 2.3 KB
- dev/data/tinyshakespeare.py 2.3 KB
- profile_gpt2.cu 2.2 KB
- doc/layernorm/layernorm.py 1.9 KB
- llmc/logger.h 1.8 KB
- llmc/cublas_common.h 1.4 KB
- scripts/run_gpt2_774M.sh 1.3 KB
- scripts/run_gpt2_350M.sh 1.3 KB
- scripts/run_gpt3_124M.sh 1.3 KB
- scripts/run_gpt2_124M.sh 1.3 KB
- llmc/sampler.h 1.1 KB
- LICENSE 1.0 KB
- scripts/pyrun_gpt2_124M.sh 876 bytes
- llmc/cudnn_att.h 799 bytes
- dev/data/README.md 618 bytes
- requirements.txt 57 bytes
Download Torrent
Related Resources
Copyright Infringement
If the content above is not authorized, please contact us via activebusinesscommunication[AT]gmail.com. Remember to include the full url in your complaint.