[release/2.7] Enable mx fp8 support on ROCm#2199
Merged
pruthvistony merged 4 commits intorelease/2.7from Jun 4, 2025
Merged
Conversation
Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com>
Author
|
rel/2.7 does not support mx fp4. Hence added ROCm support to enable mx fp8. |
Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com>
Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com>
pruthvistony
approved these changes
Jun 4, 2025
pragupta
pushed a commit
that referenced
this pull request
Jul 21, 2025
Ported mx fp8 part from #2046 Current test stats (accounting only blockwise scale tests) PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v Ran 225 tests in 8.256s FAILED (failures=1, skipped=150) _74 test pass_ **fp8 mx data type sample test case.** test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (__main__.TestFP8MatmulCudaCUDA) hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0 --------- Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com> (cherry picked from commit d17e222)
pragupta
pushed a commit
to pragupta/pytorch
that referenced
this pull request
Jul 21, 2025
Ported mx fp8 part from ROCm#2046 Current test stats (accounting only blockwise scale tests) PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v Ran 225 tests in 8.256s FAILED (failures=1, skipped=150) _74 test pass_ **fp8 mx data type sample test case.** test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (__main__.TestFP8MatmulCudaCUDA) hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0 --------- Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com> (cherry picked from commit d17e222)
pragupta
pushed a commit
that referenced
this pull request
Jul 22, 2025
Ported mx fp8 part from #2046 Current test stats (accounting only blockwise scale tests) PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v Ran 225 tests in 8.256s FAILED (failures=1, skipped=150) _74 test pass_ **fp8 mx data type sample test case.** test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (__main__.TestFP8MatmulCudaCUDA) hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0 --------- Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com> (cherry picked from commit d17e222)
jithunnair-amd
pushed a commit
that referenced
this pull request
Jul 22, 2025
Ported mx fp8 part from #2046 Current test stats (accounting only blockwise scale tests) PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v Ran 225 tests in 8.256s FAILED (failures=1, skipped=150) _74 test pass_ **fp8 mx data type sample test case.** test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (__main__.TestFP8MatmulCudaCUDA) hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0 --------- Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com> (cherry picked from commit d17e222)
pragupta
pushed a commit
that referenced
this pull request
Jul 29, 2025
Ported mx fp8 part from #2046 Current test stats (accounting only blockwise scale tests) PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v Ran 225 tests in 8.256s FAILED (failures=1, skipped=150) _74 test pass_ **fp8 mx data type sample test case.** test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (__main__.TestFP8MatmulCudaCUDA) hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0 --------- Signed-off-by: Jagadish Krishnamoorthy <jagadish.krishnamoorthy@amd.com> (cherry picked from commit d17e222)
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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.
Ported mx fp8 part from #2046
Current test stats (accounting only blockwise scale tests)
PYTORCH_TEST_WITH_ROCM=1 python test/test_matmul_cuda.py -k test_blockwise -v
Ran 225 tests in 8.256s
FAILED (failures=1, skipped=150)
74 test pass
fp8 mx data type sample test case.
test_blockwise_mxfp8_numerics_test_case_name_data_random_scales_one_fast_accum_True_512_128_256_cuda (main.TestFP8MatmulCudaCUDA)
hipblaslt-bench --api_method c -m 256 -n 512 -k 128 --lda 128 --ldb 128 --ldc 256 --ldd 256 --stride_a 0 --stride_b 0 --stride_c 0 --stride_d 0 --alpha 1 --beta 0 --transA T --transB N --batch_count 1 --scaleA 3 --scaleB 3 --a_type f8_r --b_type f8_r --c_type bf16_r --d_type bf16_r --compute_type f32_r --algo_method index --solution_index -2146957310 --rotating 0 --cold_iters 0 --iters 0