Add NoQEngine fallback for quantized ops on RISC-V#15
Open
XYenChi wants to merge 14 commits into
Open
Conversation
* Add RISC-V 64 BLOCK_LIST * Skip long time testcase
* Add riscv64 ci with PR
⭐ Run Main Diff base and head Push to riscv From https://github.com/RuyiAI-Stack/pytorch * branch riscv -> FETCH_HEAD fatal: Not a valid object name origin/main Error: ❌ Failure - Main Diff base and head Error: exit status 128
* mklnn is unavailable on RISC-V * Remove test_cpu_select_algorithm from block_list * Fix block list format
bytes_to_scalar previously round-tripped raw bytes through Python
float/complex values (via ctypes) before constructing the tensor. This
loses NaN bit patterns on architectures (such as RISC-V) that
canonicalize NaNs in floating-point loads/conversions, causing
test_bytes_to_scalar_cpu_{float32,float64,complex64,complex128} to
fail with mismatched storage bytes.
Construct the scalar tensor by writing the raw bytes directly into its
untyped storage so all input bit patterns (including NaN payloads) are
preserved exactly.
These cases are too slow on riscv64, adding them to here simply Drop test_torch from the list because it is one core case
bytes_to_scalar previously round-tripped raw bytes through Python
float/complex values (via ctypes) before constructing the tensor. This
loses NaN bit patterns on architectures (such as RISC-V) that
canonicalize NaNs in floating-point loads/conversions, causing
test_bytes_to_scalar_cpu_{float32,float64,complex64,complex128} to
fail with mismatched storage bytes.
Construct the scalar tensor by writing the raw bytes directly into its
untyped storage so all input bit patterns (including NaN payloads) are
preserved exactly.
Fix bytes_to_scalar for float/complex on RISC-V
Implement PackedLinearWeightNoQEngine and PackedConvWeightNoQEngine classes that dequantize inputs, run float computation, and requantize outputs. This provides a working fallback when no hardware-specific quantized engine (FBGEMM, QNNPACK, ONEDNN) is available. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
WuXintong123
force-pushed
the
riscv
branch
2 times, most recently
from
3a5cb48 to
4bbc281
Compare
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.
Implement PackedLinearWeightNoQEngine and PackedConvWeightNoQEngine classes that dequantize inputs, run float computation, and requantize outputs. This provides a working fallback when no hardware-specific quantized engine (FBGEMM, QNNPACK, ONEDNN) is available.