aakhundov
/ flex_attention_fwd.py
Created
September 30, 2025 21:28
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
| # AOT ID: ['1_inference'] | |
| import triton | |
| import triton.language as tl | |
| import torch | |
| from torch._C import _cuda_getCurrentRawStream as get_raw_stream | |
| from torch._inductor.runtime.benchmarking import benchmarker | |
| aten = torch.ops.aten |
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
| module attributes {"triton_gpu.num-ctas" = 1 : i32, "triton_gpu.num-warps" = 2 : i32, triton_gpu.target = "cuda:90", "triton_gpu.threads-per-warp" = 32 : i32} { | |
| tt.func public @_ragged_hstu_attn_fwd(%arg0: !tt.ptr<bf16> {tt.divisibility = 16 : i32}, %arg1: !tt.ptr<bf16> {tt.divisibility = 16 : i32}, %arg2: !tt.ptr<bf16> {tt.divisibility = 16 : i32}, %arg3: !tt.ptr<i64> {tt.divisibility = 16 : i32}, %arg4: !tt.ptr<i64> {tt.divisibility = 16 : i32}, %arg5: !tt.ptr<bf16> {tt.divisibility = 16 : i32}, %arg6: !tt.ptr<bf16> {tt.divisibility = 16 : i32}, %arg7: i32 {tt.divisibility = 16 : i32}, %arg8: i32 {tt.divisibility = 16 : i32}, %arg9: i32 {tt.divisibility = 16 : i32}, %arg10: i32 {tt.divisibility = 16 : i32}, %arg11: i32 {tt.divisibility = 16 : i32}, %arg12: i32 {tt.divisibility = 16 : i32}, %arg13: i32 {tt.divisibility = 16 : i32}, %arg14: i32 {tt.divisibility = 16 : i32}, %arg15: i32 {tt.divisibility = 16 : i32}, %arg16: f32, %arg17: i32, %arg18: i32 {tt.divisibility = 16 : i32}, %arg19: i32 {tt.divisibil |
aakhundov
/ triton_none_arg.py
Created
September 5, 2024 21:53
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
| import triton | |
| import triton.language as tl | |
| @triton.autotune( # E: Untyped decorator makes function "sin_kernel" untyped [misc] | |
| configs=[ | |
| triton.Config({'BLOCK_SIZE': 32}, num_stages=5, num_warps=2), | |
| triton.Config({'BLOCK_SIZE': 64}, num_stages=4, num_warps=4), | |
| ], | |
| key=['n_elements'] | |
| ) |
aakhundov
/ llama_v2_7b_16h_26740f8.py
Created
March 16, 2024 00:28
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
| from ctypes import c_void_p, c_long | |
| import torch | |
| import math | |
| import random | |
| import os | |
| import tempfile | |
| from math import inf, nan | |
| from torch._inductor.hooks import run_intermediate_hooks | |
| from torch._inductor.utils import maybe_profile |
aakhundov
/ llama_v2_7b_16h_3d089de.py
Created
March 16, 2024 00:28
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
| from ctypes import c_void_p, c_long | |
| import torch | |
| import math | |
| import random | |
| import os | |
| import tempfile | |
| from math import inf, nan | |
| from torch._inductor.hooks import run_intermediate_hooks | |
| from torch._inductor.utils import maybe_profile |
aakhundov
/ llama_v2_7b_16h.py
Created
March 16, 2024 00:26
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
| from ctypes import c_void_p, c_long | |
| import torch | |
| import math | |
| import random | |
| import os | |
| import tempfile | |
| from math import inf, nan | |
| from torch._inductor.hooks import run_intermediate_hooks | |
| from torch._inductor.utils import maybe_profile |
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
| from ctypes import c_void_p, c_long | |
| import torch | |
| import math | |
| import random | |
| import os | |
| import tempfile | |
| from math import inf, nan | |
| from torch._inductor.hooks import run_intermediate_hooks | |
| from torch._inductor.utils import maybe_profile |
aakhundov
/ test_cond_nested_abi_compatible_cuda.cpp
Created
March 7, 2024 17:44
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
| #include <torch/csrc/inductor/aoti_runtime/arrayref_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/interface.h> | |
| #include <torch/csrc/inductor/aoti_runtime/model_container.h> | |
| #include <torch/csrc/inductor/aoti_runtime/scalar_to_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/thread_local.h> | |
| #include <iostream> | |
| #include <sstream> | |
| #include <stdexcept> | |
| #include <vector> |
aakhundov
/ test_cond_with_multiple_outputs_abi_compatible_cuda.cpp
Created
March 7, 2024 17:39
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
| #include <torch/csrc/inductor/aoti_runtime/arrayref_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/interface.h> | |
| #include <torch/csrc/inductor/aoti_runtime/model_container.h> | |
| #include <torch/csrc/inductor/aoti_runtime/scalar_to_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/thread_local.h> | |
| #include <iostream> | |
| #include <sstream> | |
| #include <stdexcept> | |
| #include <vector> |
aakhundov
/ test_cond_with_parameters_abi_compatible_cuda.cpp
Created
March 7, 2024 17:38
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
| #include <torch/csrc/inductor/aoti_runtime/arrayref_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/interface.h> | |
| #include <torch/csrc/inductor/aoti_runtime/model_container.h> | |
| #include <torch/csrc/inductor/aoti_runtime/scalar_to_tensor.h> | |
| #include <torch/csrc/inductor/aoti_runtime/thread_local.h> | |
| #include <iostream> | |
| #include <sstream> | |
| #include <stdexcept> | |
| #include <vector> |
NewerOlder