facebookincubator/AITemplate issues and pull requests

#1032 - c10::nullopt -> std::nullopt

Pull Request - State: closed - Opened by r-barnes about 1 month ago - 1 comment
Labels: CLA Signed, fb-exported

#1031 - Break down test_group_fused_layernorm_sigmoid_mul to avoid timeout

Pull Request - State: closed - Opened by henrylhtsang about 1 month ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1030 - Convert directory fbcode/aitemplate to use the Ruff Formatter

Pull Request - State: open - Opened by tpolasek about 1 month ago - 2 comments
Labels: CLA Signed, module: rocm, fb-exported

#1029 - Added a 'use cases' section

Pull Request - State: open - Opened by chillinturt 2 months ago - 1 comment

#1028 - Update default CUDA version to 12.4

Pull Request - State: open - Opened by zhuhan0 2 months ago - 2 comments
Labels: CLA Signed, fb-exported

#1027 - FileNotFoundError: [Errno 2] No such file or directory: \\ComfyUI\\custom_nodes\\AITemplate-main\\init.py'

Issue - State: open - Opened by DuckersMcQuack 2 months ago

#1026 - AI-Driven Enhancements for Dynamic Benchmarking and Performance Optimization

Pull Request - State: open - Opened by RahulVadisetty91 2 months ago - 1 comment

#1025 - Allow Passing in Size of Dynamic Dimensions to Inference Function

Pull Request - State: closed - Opened by oniononion36 3 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#1024 - Called SetConstant on， but can't find in either bound or unbound constant set

Issue - State: open - Opened by ADongGu 3 months ago

#1023 - Add reciprocal operator

Pull Request - State: closed - Opened by muchulee8 3 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#1022 - Use the full header file path to fix the build

Pull Request - State: closed - Opened by hl475 3 months ago - 4 comments
Labels: CLA Signed, fb-exported, Merged

#1021 - Grouped Transposed Convolutions cutlass errror

Issue - State: open - Opened by jonpryai 3 months ago

#1020 - Process separate q/k/v weights in MHA converter

Pull Request - State: closed - Opened by aakhundov 4 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1019 - Make V100 tests runnable on {A,H}100 in Sandcastle CI

Pull Request - State: closed - Opened by aakhundov 4 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1018 - Prevent erroneous deduping of the full op

Pull Request - State: closed - Opened by aakhundov 4 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#1017 - Add max_acc_splits

Pull Request - State: closed - Opened by qxy11 4 months ago - 8 comments
Labels: CLA Signed, fb-exported, Merged

#1016 - Del using namespace aitemplate/AITemplate/static/include/kernels/mem_eff_attention/kernel_forward.h

Pull Request - State: open - Opened by r-barnes 4 months ago - 1 comment
Labels: CLA Signed, fb-exported

#1015 - add eager mode check for NaN and Inf

Pull Request - State: closed - Opened by frank-wei 4 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1014 - Del using namespace aitemplate/AITemplate/static/include/kernels/mem_eff_attention/kernel_forward.h

Pull Request - State: open - Opened by r-barnes 4 months ago - 1 comment
Labels: CLA Signed, fb-exported

#1012 - add cuda_graph for mts_gpu_benchmark

Pull Request - State: closed - Opened by frank-wei 5 months ago - 6 comments
Labels: CLA Signed, fb-exported, Merged

#1011 - Handle size-0 output for split

Pull Request - State: closed - Opened by muchulee8 5 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1010 - allow concatenating empty tensors

Pull Request - State: closed - Opened by chenyang78 6 months ago - 6 comments
Labels: CLA Signed, Merged

#1009 - Confused on the shape of input Tensor

Issue - State: closed - Opened by ningmenghongcha 6 months ago - 7 comments

#1008 - Use torch.all to check tensor equality

Pull Request - State: closed - Opened by 22quinn 6 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1007 - c10::optional -> std::optional in aiplatform/distributed_inference/pytorch/ops/tests/distributed_inference_operators_test_fixture.h +20

Pull Request - State: closed - Opened by r-barnes 7 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#1006 - Fix minimizer tests

Pull Request - State: closed - Opened by zejunh 7 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#1005 - standalone find_batch_size_dim

Pull Request - State: closed - Opened by hl475 7 months ago - 7 comments
Labels: CLA Signed, fb-exported, Merged

#1004 - Range operator lowering minimizer

Pull Request - State: open - Opened by frank-wei 7 months ago - 1 comment
Labels: CLA Signed, fb-exported

#1003 - include cstdint for int*_t in profiler

Pull Request - State: open - Opened by chengscott 7 months ago - 4 comments
Labels: CLA Signed

#1002 - Disable AITModel in fx2ait on AMD

Pull Request - State: open - Opened by zoranzhao 7 months ago
Labels: CLA Signed

#1001 - Update OSS black linter version to 24.4.0

Pull Request - State: closed - Opened by aakhundov 7 months ago - 6 comments
Labels: CLA Signed, fb-exported, Merged

#1000 - Skip fuse_mm_elementwise fusion with model output in the middle

Pull Request - State: closed - Opened by aakhundov 7 months ago - 5 comments
Labels: CLA Signed, fb-exported, Merged

#999 - model_interface.cu:231: Error: Constant pretrained_model_patch_embed_proj_weight was not set! Set the value with set_constant.

Issue - State: closed - Opened by ADongGu 8 months ago - 1 comment

#998 - Got cutlass error: Error Internal at: 214

Issue - State: closed - Opened by syntrive 8 months ago - 2 comments

#997 - Docker image fails to build due to python dependency issue

Issue - State: open - Opened by M1kep 8 months ago - 2 comments

#996 - Fixed a couple of dynamic shape detection issues

Pull Request - State: closed - Opened by chenyang78 9 months ago - 5 comments
Labels: CLA Signed, fb-exported, Merged

#995 - Does Concatenate order matters?

Issue - State: open - Opened by ecilay 9 months ago - 1 comment

#994 - Add floor op

Pull Request - State: open - Opened by henryhu6 9 months ago - 3 comments
Labels: CLA Signed, fb-exported

#993 - Add log1p elementwise op

Pull Request - State: open - Opened by 22quinn 9 months ago - 5 comments
Labels: CLA Signed, fb-exported

#992 - ait: Explicitly throw when indexing a boolean tensor for masking

Pull Request - State: closed - Opened by kflu 10 months ago - 7 comments
Labels: CLA Signed, fb-exported, Merged

#991 - Model is successfully compiled, but OOM when loading

Issue - State: open - Opened by jiangwei221 10 months ago

#990 - windows platform cannot link _binary_constants_bin_end and _binary_constants_bin_start

Issue - State: closed - Opened by joye 10 months ago - 5 comments

#989 - Extend int dtype with uint8 to skip lowering uint8-input ops in AIT splitter

Pull Request - State: closed - Opened by zoranzhao 10 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#988 - multi-gpu at runtime error

Issue - State: open - Opened by ecilay 10 months ago - 4 comments

#987 - allow binary ops where only one arg is an immutable IntVarTensor

Pull Request - State: closed - Opened by bradleyhd 10 months ago - 5 comments
Labels: CLA Signed, fb-exported, Merged

#986 - add support for permute call with tuple args

Pull Request - State: closed - Opened by bradleyhd 10 months ago - 4 comments
Labels: CLA Signed, fb-exported, Merged

#985 - allow type promotions from bool if common type is non-bool

Pull Request - State: closed - Opened by bradleyhd 10 months ago - 4 comments
Labels: CLA Signed, fb-exported, Merged

#984 - fbcode//aitemplate/AITemplate

Pull Request - State: closed - Opened by bajanduncan 11 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#983 - Does AIT handle if/else in forward function?

Issue - State: open - Opened by jiangwei221 11 months ago - 1 comment

#982 - AIT softmax fix

Pull Request - State: closed - Opened by zoranzhao 11 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#981 - `Unsupported workload for this conv2d specialization` when using dynamic shape together with permute

Issue - State: closed - Opened by jiangwei221 11 months ago - 6 comments

#980 - gcc: internal compiler error

Issue - State: closed - Opened by jiangwei221 11 months ago - 2 comments

#979 - add avg_pool3d converter

Pull Request - State: closed - Opened by colinchan15 12 months ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#978 - aitemplate/AITemplate

Pull Request - State: closed - Opened by zsol 12 months ago - 2 comments
Labels: CLA Signed, fb-exported, Merged

#977 - Add fuse_single_source_parallel_gemm

Pull Request - State: closed - Opened by muchulee8 12 months ago - 5 comments
Labels: CLA Signed, fb-exported, Merged

#976 - `Fatal Python error: Floating point exception` with `run_with_tensors`

Issue - State: closed - Opened by jiangwei221 12 months ago - 3 comments

#975 - <class 'src.pipeline_stable_diffusion_ait.StableDiffusionAITPipeline'> is incorrectly implemented. Expected {'feature_extractor', 'scheduler', 'tokenizer', 'text_encoder', 'safety_checker', 'unet', 'vae'} to be defined

Issue - State: open - Opened by jiagaoxiang 12 months ago - 4 comments

#974 - gemm_gen_profiler() takes 3 positional arguments but 4 were given

Issue - State: closed - Opened by jiagaoxiang 12 months ago - 2 comments

#973 - Merging upstream updates

Pull Request - State: closed - Opened by isouf about 1 year ago - 1 comment

#972 - Failed to compile the controlnet: thepowefuldeez/sd21-controlnet-canny

Issue - State: open - Opened by chengdianxuezi about 1 year ago - 1 comment

#971 - Remove cuda sync at end of mem_eff_attention

Pull Request - State: closed - Opened by henryhu6 about 1 year ago - 3 comments
Labels: CLA Signed, fb-exported, Merged

#970 - Handle an input spec with first dim equal to zero

Pull Request - State: open - Opened by khabinov about 1 year ago - 2 comments
Labels: CLA Signed, fb-exported

#969 - disable maskedSelectTestCase.test_fp32_input_broadcast_shape_4

Pull Request - State: closed - Opened by chenyang78 about 1 year ago - 2 comments
Labels: CLA Signed, Merged

#968 - error during inferencing: Error: Constant embeddings_token_embedding_weight was not set! Set the value with set_constant.

Issue - State: open - Opened by mengbingrock about 1 year ago - 2 comments

GitHub / facebookincubator/AITemplate issues and pull requests