| .. |
|
sharded_moe
|
Fix MoE tensor parallelism tests (#20147)
|
2024-03-29 16:10:09 -07:00 |
|
test_data
|
Update ruff and clang-format versions (#21479)
|
2024-07-24 11:50:11 -07:00 |
|
benchmark_gqa.py
|
[CUDA] Benchmark GQA on popular LLM models (#20646)
|
2024-05-10 14:14:15 -07:00 |
|
benchmark_gqa_windows.py
|
Make Flash Attention work on Windows (#21015)
|
2024-06-24 09:43:49 -07:00 |
|
benchmark_mha.cmd
|
Update benchmark_mha.py to compare with PyTorch SDPA (#21449)
|
2024-07-26 18:45:14 -07:00 |
|
benchmark_mha.py
|
[CUDA] Fix MHA mask (#21655)
|
2024-08-09 01:31:00 -07:00 |
|
benchmark_mha.sh
|
Update benchmark_mha.py to compare with PyTorch SDPA (#21449)
|
2024-07-26 18:45:14 -07:00 |
|
bert_model_generator.py
|
Bump ruff to 0.3.2 and black to 24 (#19878)
|
2024-03-13 10:00:32 -07:00 |
|
bert_padding.py
|
|
|
|
conformer_model_generator.py
|
Bump ruff to 0.3.2 and black to 24 (#19878)
|
2024-03-13 10:00:32 -07:00 |
|
conftest.py
|
|
|
|
gpt2_model_generator.py
|
Bump ruff to 0.3.2 and black to 24 (#19878)
|
2024-03-13 10:00:32 -07:00 |
|
model_loader.py
|
|
|
|
parity_utilities.py
|
|
|
|
rotary_flash.py
|
Update ruff and clang-format versions (#21479)
|
2024-07-24 11:50:11 -07:00 |
|
test_attention_fusion.py
|
|
|
|
test_conformer.py
|
|
|
|
test_embedlayer_fusion.py
|
|
|
|
test_flash_attn_cuda.py
|
Make Flash Attention work on Windows (#21015)
|
2024-06-24 09:43:49 -07:00 |
|
test_flash_attn_rocm.py
|
[ROCM] adjust test_flash_attn_rocm test tolerance (#21379)
|
2024-07-17 07:35:12 -07:00 |
|
test_gelu_fusions.py
|
Add fusions for OpenAI CLIP (#20721)
|
2024-05-18 08:27:16 -07:00 |
|
test_gemmfastgelu_fusion.py
|
|
|
|
test_generation.py
|
Fix typos according to reviewdog report. (#21335)
|
2024-07-22 13:37:32 -07:00 |
|
test_gpt2_benchmark.py
|
|
|
|
test_gpt2_to_onnx.py
|
|
|
|
test_gqa_cpu.py
|
fix integer overflow in Attention (#20921)
|
2024-06-05 10:19:26 -07:00 |
|
test_group_norm.py
|
|
|
|
test_mha.py
|
[CUDA] Fix MHA mask (#21655)
|
2024-08-09 01:31:00 -07:00 |
|
test_onnx_utils.py
|
Add ModelProto support for transformers optimize_model (#19990)
|
2024-03-22 18:40:58 -07:00 |
|
test_optimizer.py
|
|
|
|
test_optimizer_stable_diffusion.py
|
|
|
|
test_parity_decoder_attention.py
|
|
|
|
test_parity_gelu.py
|
|
|
|
test_parity_huggingface_gpt_attention.py
|
|
|
|
test_parity_layernorm.py
|
|
|
|
test_parity_mixtral_moe.py
|
Fix Mixtral Parity test to keep it consistent with Transformers. (#20210)
|
2024-04-08 13:04:12 -07:00 |
|
test_parity_moe.py
|
Make Flash Attention work on Windows (#21015)
|
2024-06-24 09:43:49 -07:00 |
|
test_parity_neox_attention.py
|
fix gqa cpu nan bug (#20521)
|
2024-05-07 15:19:26 -07:00 |
|
test_parity_rotary_embedding.py
|
|
|
|
test_parity_t5_mha.py
|
|
|
|
test_profiler.py
|
|
|
|
test_rotary_embedding_fusion.py
|
|
|
|
test_rotary_mha_fusion.py
|
|
|
|
test_shape_infer_helper.py
|
|
|
|
test_simplified_layernorm_fusion.py
|
|
|
|
test_skip_layer_norm_fusion.py
|
|
|
|
test_sparse_attention.py
|
[CPU] SparseAttention op (#21110)
|
2024-07-03 21:51:57 -07:00 |
|
test_whisper.py
|
|
|
|
test_whisper_timestamp_processor.py
|
|
|
|
whisper_model_generator.py
|
Bump ruff to 0.3.2 and black to 24 (#19878)
|
2024-03-13 10:00:32 -07:00 |
