[ET-VK][ez] Handle zero-element tensors when building Vulkan graph #12021
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
…fers Pull Request resolved: #11983 ## Changes * Move the logic skipping output nodes that are mutable buffers from runtime to AOT ## Context A `fx.Graph` may return nodes that are mutable buffers: ``` class GraphModule(torch.nn.Module): def forward(self, p_wrapped_module_wq_weight: "f32[2048, 2048]", p_wrapped_module_wk_weight: "f32[512, 2048]", p_wrapped_module_wv_weight: "f32[512, 2048]", p_wrapped_module_wo_weight: "f32[2048, 2048]", b_wrapped_module_kv_cache_k_cache: "f32[1, 2048, 8, 64]", b_wrapped_module_kv_cache_v_cache: "f32[1, 2048, 8, 64]", x: "f32[1, s27, 2048]", freqs_cos: "f32[s27, 32]", freqs_sin: "f32[s27, 32]", input_pos: "i64[1]"): sym_size: "Sym(s27)" = torch.ops.aten.sym_size.int(x, 1) ... # b_wrapped_module_kv_cache_*_cache are mutable buffers # getitem_2 and getitem_3 are derived from mutable buffers, hence they are # themselves mutable buffers auto_functionalized = torch.ops.higher_order.auto_functionalized(torch.ops.llama.update_cache.default, value = getitem_1, cache = b_wrapped_module_kv_cache_k_cache, start_pos = _local_scalar_dense_1); getitem_1 = b_wrapped_module_kv_cache_k_cache = None getitem_2: "f32[1, 2048, 8, 64]" = auto_functionalized[1]; auto_functionalized = None auto_functionalized_1 = torch.ops.higher_order.auto_functionalized(torch.ops.llama.update_cache.default, value = aten_view_copy_default_8, cache = b_wrapped_module_kv_cache_v_cache, start_pos = _local_scalar_dense_1); aten_view_copy_default_8 = b_wrapped_module_kv_cache_v_cache = _local_scalar_dense_1 = None getitem_3: "f32[1, 2048, 8, 64]" = auto_functionalized_1[1]; auto_functionalized_1 = None ... aten_permute_copy_default_3: "f32[2048, 2048]" = executorch_exir_dialects_edge__ops_aten_permute_copy_default(p_wrapped_module_wo_weight, [1, 0]); p_wrapped_module_wo_weight = None aten_view_copy_default_10: "f32[s27, 2048]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_view_copy_default_9, [sym_size, 2048]); aten_view_copy_default_9 = None aten_mm_default_3: "f32[s27, 2048]" = executorch_exir_dialects_edge__ops_aten_mm_default(aten_view_copy_default_10, aten_permute_copy_default_3); aten_view_copy_default_10 = aten_permute_copy_default_3 = None aten_view_copy_default_11: "f32[1, s27, 2048]" = executorch_exir_dialects_edge__ops_aten_view_copy_default(aten_mm_default_3, [1, sym_size, 2048]); aten_mm_default_3 = sym_size = None # getitem_2 and getitem_3 are returned as outputs, presumably to prevent the # update_cache calls from being removed due to dead code elimination return (getitem_2, getitem_3, aten_view_copy_default_11, None) ``` In the graph signature of the `ExportedProgram` these show up as `BUFFER_MUTATION` outputs ``` Graph signature: # inputs p_wrapped_module_wq_weight: PARAMETER target='wrapped_module.wq.weight' p_wrapped_module_wk_weight: PARAMETER target='wrapped_module.wk.weight' p_wrapped_module_wv_weight: PARAMETER target='wrapped_module.wv.weight' p_wrapped_module_wo_weight: PARAMETER target='wrapped_module.wo.weight' b_wrapped_module_kv_cache_k_cache: BUFFER target='wrapped_module.kv_cache.k_cache' persistent=True b_wrapped_module_kv_cache_v_cache: BUFFER target='wrapped_module.kv_cache.v_cache' persistent=True x: USER_INPUT freqs_cos: USER_INPUT freqs_sin: USER_INPUT input_pos: USER_INPUT # outputs getitem_2: BUFFER_MUTATION target='wrapped_module.kv_cache.k_cache' getitem_3: BUFFER_MUTATION target='wrapped_module.kv_cache.v_cache' aten_view_copy_default_11: USER_OUTPUT : USER_OUTPUT ``` Although these nodes are technically returned by the `fx.Graph`, `BUFFER_MUTATION` outputs are not included in the delegate call schema. Since the Vulkan delegate serialization uses the output node to mark which values are returned as outputs, this could result in a mismatch betwen the outputs of the Vulkan delegate and the outputs expected by the ExecuTorch runtime. ## Motivation Previously, this mismatch was addressed in the runtime, by skipping the processing of non-tensor outputs. However, this solution does not account for the fact that in some models, paramters of the model may be returned as outputs. In this case, those parameter outputs would be skipped but the ExecuTorch runtime would still expect to receive them as outputs. To solve the problem properly, this diff changes the serialization logic to check if an output node is a mutable buffer, and skip marking it as an output if so. In the runtime, all output nodes are processed instead of only processing tensor outputs. ghstack-source-id: 292864908 @exported-using-ghexport Differential Revision: [D77281491](https://our.internmc.facebook.com/intern/diff/D77281491/)
Pull Request resolved: #11984 ## Changes As title. ## Motivation Some models may have parameter tensors which are zero-shape (i.e. no elements). In this case, trying to serialize the tensor data will result in a null pointer exception. ghstack-source-id: 292864904 Differential Revision: [D77281492](https://our.internmc.facebook.com/intern/diff/D77281492/)
pytorch-bot
bot
added
the
module: vulkan
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/12021
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 New FailureAs of commit e5e3467 with merge base ecb85ce ( NEW FAILURE - The following job has failed:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR was created by the merge bot to help merge the original PR into the main branch.
ghstack PR number: #11984 by @SS-JIA
^ Please use this as the source of truth for the PR details, comments, and reviews
ghstack PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/250/base
ghstack PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/250/head
Merge bot PR base: https://github.com/pytorch/executorch/tree/gh/SS-JIA/249/orig
Merge bot PR head: https://github.com/pytorch/executorch/tree/gh/SS-JIA/250/orig
@diff-train-skip-merge
cc @SS-JIA @manuelcandales @cbilgin