Skip to content

Activity

Convert directory fbcode/aitemplate to use the Ruff Formatter (#1033)

facebook-github-botpushed 1 commit to main • c7e0101…f711356 • 
on Dec 4, 2024

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

facebook-github-botpushed 1 commit to main • aef8f6e…c7e0101 • 
on Oct 23, 2024

Break down test_group_fused_layernorm_sigmoid_mul to avoid timeout (#…

facebook-github-botpushed 1 commit to main • 437b48a…aef8f6e • 
on Oct 18, 2024

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

facebook-github-botpushed 1 commit to main • bfb1dc2…437b48a • 
on Sep 13, 2024

Add reciprocal operator (#1023)

facebook-github-botpushed 1 commit to main • e2eff07…bfb1dc2 • 
on Sep 4, 2024

Use the full header file path to fix the build (#1022)

facebook-github-botpushed 1 commit to main • 4360ae3…e2eff07 • 
on Aug 27, 2024

Add max_acc_splits (#1017)

facebook-github-botpushed 1 commit to main • 7b41778…4360ae3 • 
on Aug 14, 2024

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

facebook-github-botpushed 1 commit to main • 2aef297…7b41778 • 
on Aug 13, 2024

Prevent erroneous deduping of the full op (#1018)

facebook-github-botpushed 1 commit to main • dc13d36…2aef297 • 
on Aug 9, 2024

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

facebook-github-botpushed 1 commit to main • bbb9b84…dc13d36 • 
on Aug 9, 2024

add eager mode check for NaN and Inf (#1015)

facebook-github-botpushed 1 commit to main • efb0ce6…bbb9b84 • 
on Jul 25, 2024

add cuda_graph for mts_gpu_benchmark (#1012)

facebook-github-botpushed 1 commit to main • a1769f2…efb0ce6 • 
on Jul 12, 2024

Handle size-0 output for split (#1011)

facebook-github-botpushed 1 commit to main • 7d427ca…a1769f2 • 
on Jun 28, 2024

allow concatenating empty tensors (#1010)

facebook-github-botpushed 1 commit to main • 95697dc…7d427ca • 
on Jun 18, 2024

Use torch.all to check tensor equality (#1008)

facebook-github-botpushed 1 commit to main • d594370…95697dc • 
on May 22, 2024

c10::optional -> std::optional in aiplatform/distributed_inference/py…

facebook-github-botpushed 1 commit to main • d158982…d594370 • 
on May 14, 2024

Fix minimizer tests (#1006)

facebook-github-botpushed 1 commit to main • 3662d77…d158982 • 
on May 10, 2024

Disable AITModel in fx2ait on AMD

facebook-github-botpushed 1 commit to main • d4b2714…3662d77 • 
on May 9, 2024

standalone find_batch_size_dim (#1005)

facebook-github-botpushed 1 commit to main • 6983d9e…d4b2714 • 
on May 8, 2024

Range operator lowering minimizer

facebook-github-botpushed 1 commit to main • 0973303…6983d9e • 
on May 8, 2024

Update OSS black linter version to 24.4.0 (#1001)

facebook-github-botpushed 1 commit to main • eb89bf6…0973303 • 
on Apr 19, 2024

Skip fuse_mm_elementwise fusion with model output in the middle (#1000)

facebook-github-botpushed 1 commit to main • d6142ef…eb89bf6 • 
on Apr 19, 2024

Apply clang-format 18

facebook-github-botpushed 1 commit to main • d2dc957…d6142ef • 
on Apr 14, 2024

Fixed a couple of dynamic shape detection issues (#996)

facebook-github-botpushed 1 commit to main • 0390a00…d2dc957 • 
on Mar 19, 2024

apply Black 2024 style in fbcode (11/16)

facebook-github-botpushed 1 commit to main • fa04b43…0390a00 • 
on Mar 3, 2024

Add log1p elementwise op

facebook-github-botpushed 1 commit to main • e608346…fa04b43 • 
on Mar 1, 2024

Add floor op

facebook-github-botpushed 1 commit to main • a99c753…e608346 • 
on Mar 1, 2024

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

facebook-github-botpushed 1 commit to main • 4b27253…a99c753 • 
on Feb 16, 2024

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

facebook-github-botpushed 1 commit to main • cc9703a…4b27253 • 
on Jan 31, 2024

add support for permute call with tuple args (#986)

facebook-github-botpushed 2 commits to main • ac56a6c…cc9703a • 
on Jan 31, 2024