Enable OCP FP8 for Latest Archs #111
Open
+455
−161
Conversation
This file contains 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
ScXfjiang
force-pushed
the
rocm-jaxlib-v0.4.35-qa_enable_ocp_fp8_in_gemm_rewriter
branch
from
93c9277 to
4d3c1f5
Compare
ScXfjiang
force-pushed
the
rocm-jaxlib-v0.4.35-qa_enable_ocp_fp8_in_gemm_rewriter
branch
6 times, most recently
from
c6320d5 to
61a5683
Compare
ScXfjiang
force-pushed
the
rocm-jaxlib-v0.4.35-qa_enable_ocp_fp8_in_gemm_rewriter
branch
2 times, most recently
from
538aed9 to
d20c818
Compare
ScXfjiang
force-pushed
the
rocm-jaxlib-v0.4.35-qa_enable_ocp_fp8_in_gemm_rewriter
branch
from
646ad3f to
a3a64ca
Compare
ScXfjiang
force-pushed
the
rocm-jaxlib-v0.4.35-qa_enable_ocp_fp8_in_gemm_rewriter
branch
from
9ed9fef to
187ca2e
Compare
| } | ||
|
|
||
| // hipBlasLt requires setting the a/b scale pointer (even a dummy one), | ||
| // otherwise no algorithms can be found for "a/b scaling". This is to be |
There was a problem hiding this comment.
Not true. What about d_scale and c_scale?
| float elem_a = | ||
| __half2float(__nv_cvt_fp8_to_halfraw(buffer_a[idx], __NV_E4M3)); | ||
| float elem_b = | ||
| __half2float(__nv_cvt_fp8_to_halfraw(buffer_b[idx], __NV_E4M3)); | ||
| #else // TENSORFLOW_USE_ROCM && TF_ROCM_VERSION >= 60300 | ||
| float elem_a = | ||
| __half2float(__hip_cvt_fp8_to_halfraw(buffer_a[idx], __HIP_E4M3)); |
There was a problem hiding this comment.
We don't have an api that converts directly to float?
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Outdated suggestions cannot be applied.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.
No description provided.