(improvement) serializers: add Cython-optimized serialization for VectorType (up to 30x faster - 823us -> 4us!) by mykaul · Pull Request #748 · scylladb/python-driver

mykaul · 2026-03-14T11:08:22Z

Summary

Adds cassandra/serializers.pyx and cassandra/serializers.pxd implementing Cython-optimized serialization that mirrors the deserializers.pyx architecture.

What's included

Scalar serializers: SerFloatType (4-byte IEEE 754), SerDoubleType (8-byte), SerInt32Type (4-byte signed) -- the three subtypes commonly used in vector columns
SerVectorType: Pre-allocates a contiguous buffer via PyBytes_FromStringAndSize(NULL, ...) and uses C-level byte swapping for float/double/int32 vectors, with a generic fallback for other subtypes
Buffer fast-path for NumPy arrays: When the input is a NumPy array with a matching dtype, Cython typed memoryviews (float[::1], double[::1], int[::1]) read directly from the buffer protocol -- bypassing Python object creation entirely
GenericSerializer: Delegates to the Python-level cqltype.serialize() classmethod for all other types
Factory functions: find_serializer(cqltype) and make_serializers(cqltypes_list) for easy lookup and batch creation

Architecture

Mirrors deserializers.pyx exactly:

Deserializer side	Serializer side
`Deserializer` base class	`Serializer` base class
`DesFloatType`, `DesDoubleType`, `DesInt32Type`	`SerFloatType`, `SerDoubleType`, `SerInt32Type`
`DesVectorType` (type-specialized)	`SerVectorType` (type-specialized)
`GenericDeserializer`	`GenericSerializer`
`find_deserializer()`	`find_serializer()`
`make_deserializers()`	`make_serializers()`

Benchmark

Measured with min() of timeit.repeat(repeat=7, number=50_000) on a quiet machine (load <2.5). Vector<float, N> serialization, comparing Python baseline (VectorType.serialize via io.BytesIO) vs Cython SerVectorType.

List/tuple inputs

Dimension	Python baseline (ns/call)	Cython (ns/call)	Speedup
`float[128]`	9926	1168	8.5x
`float[1536]`	110569	8097	13.7x

NumPy float32 array inputs (buffer fast-path)

Dimension	Cython list (ns/call)	Cython NumPy (ns/call)	Speedup vs list
`float[128]`	1168	507	2.3x
`float[1536]`	8097	1365	5.9x

End-to-end: NumPy vs Python baseline

Dimension	Python baseline (ns/call)	Cython+NumPy (ns/call)	Speedup
`float[128]`	9926	507	19.6x
`float[1536]`	110569	1365	81.0x

Tests

Comprehensive Cython serializer unit tests in tests/unit/cython/test_serializers.py
Full unit test suite passes (740 passed, 43 skipped)

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

Copilot

Pull request overview

This PR introduces a new Cython extension module to accelerate CQL value serialization—especially VectorType—using the same general “typed Serializer object + factory lookup” approach as the existing Cython deserialization stack.

Changes:

Add cassandra/serializers.pyx implementing Cython serializers for FloatType, DoubleType, Int32Type, and an optimized VectorType serializer with generic fallback.
Add find_serializer() / make_serializers() factory helpers for serializer creation.
Add cassandra/serializers.pxd to expose the Serializer interface to other Cython modules.

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 8 comments.

File	Description
cassandra/serializers.pyx	New Cython-optimized serialization implementations and factory lookup.
cassandra/serializers.pxd	Cython declarations for the `Serializer` interface.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

…lizers Address all 8 Copilot review comments on PR scylladb#748: - Add _check_float_range() for float overflow detection matching struct.pack - Add _check_int32_range() for int32 bounds checking before C cast - Wire bounds checks into SerFloatType, SerInt32Type, and VectorType fast-paths - Replace malloc/free with PyBytes_FromStringAndSize(NULL,n)+PyBytes_AS_STRING - Add empty vector early return (b'') before allocation - Remove unused uint32_t cimport and libc.stdlib import - Add comprehensive test suite (67 tests) covering equivalence, overflow, special values, vectors, round-trips, and factory functions

Copilot

Pull request overview

Adds a new Cython serialization module to speed up VectorType (and a few common scalar subtypes) while keeping wire-format output identical to existing cqltypes.*.serialize() implementations.

Changes:

Introduce cassandra/serializers.pyx + .pxd implementing Serializer classes, including a specialized SerVectorType with float/double/int32 fast-paths.
Add serializer lookup/batch factories (find_serializer, make_serializers).
Add unit tests validating byte-for-byte equivalence and basic round-trips for the new serializers.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 7 comments.

File	Description
`cassandra/serializers.pyx`	New Cython serializers, including optimized `VectorType` serialization and factory lookup functions.
`cassandra/serializers.pxd`	Cython declarations for the `Serializer` base class.
`tests/unit/test_serializers.py`	New unit tests covering scalar/vector equivalence, round-trips, and factory behavior.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

Copilot

Pull request overview

Adds a new Cython extension module (cassandra.serializers) that provides optimized serialization implementations for common scalar types and VectorType, intended to mirror the existing deserializers.pyx architecture and improve vector-heavy workloads.

Changes:

Introduces cassandra/serializers.pyx + .pxd implementing Serializer classes, SerVectorType, and factory helpers (find_serializer, make_serializers).
Adds unit tests validating byte-for-byte equivalence vs. Python cqltype.serialize() and basic factory behavior.
Implements float/double/int32 vector fast-paths via preallocated contiguous buffers and endian swapping.

Reviewed changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated 6 comments.

File	Description
`cassandra/serializers.pyx`	New Cython-optimized serializers, including `VectorType` specialized paths and serializer lookup/factory functions.
`cassandra/serializers.pxd`	Cython declarations for the `Serializer` base class API.
`tests/unit/test_serializers.py`	New tests for serializer equivalence, edge cases, and factory helpers under Cython.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

…lizers Address all 8 Copilot review comments on PR scylladb#748: - Add _check_float_range() for float overflow detection matching struct.pack - Add _check_int32_range() for int32 bounds checking before C cast - Wire bounds checks into SerFloatType, SerInt32Type, and VectorType fast-paths - Replace malloc/free with PyBytes_FromStringAndSize(NULL,n)+PyBytes_AS_STRING - Add empty vector early return (b'') before allocation - Remove unused uint32_t cimport and libc.stdlib import - Add comprehensive test suite (67 tests) covering equivalence, overflow, special values, vectors, round-trips, and factory functions

Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 5 comments.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

mykaul · 2026-03-26T14:52:38Z

CI flakiness above - fix sent - #767

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

Restore serializers.pyx/pxd from the PR scylladb#748 branch and add SerDateType that serializes datetime/date/numeric values to 8-byte big-endian int64 millisecond timestamps entirely in C, avoiding Python-level struct.pack. Uses the same timedelta arithmetic as the pure-Python DateType.serialize (Item B) but with C-level int64 byte-swapping. Benchmark shows ~1.5x speedup over the already-optimized Python path for datetime serialization (253 ns vs 381 ns per call).

…lizers Address all 8 Copilot review comments on PR scylladb#748: - Add _check_float_range() for float overflow detection matching struct.pack - Add _check_int32_range() for int32 bounds checking before C cast - Wire bounds checks into SerFloatType, SerInt32Type, and VectorType fast-paths - Replace malloc/free with PyBytes_FromStringAndSize(NULL,n)+PyBytes_AS_STRING - Add empty vector early return (b'') before allocation - Remove unused uint32_t cimport and libc.stdlib import - Add comprehensive test suite (67 tests) covering equivalence, overflow, special values, vectors, round-trips, and factory functions

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

Restore serializers.pyx/pxd from the PR scylladb#748 branch and add SerDateType that serializes datetime/date/numeric values to 8-byte big-endian int64 millisecond timestamps entirely in C, avoiding Python-level struct.pack. Uses the same timedelta arithmetic as the pure-Python DateType.serialize (Item B) but with C-level int64 byte-swapping. Benchmark shows ~1.5x speedup over the already-optimized Python path for datetime serialization (253 ns vs 381 ns per call).

…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

…torType Add cassandra/serializers.pyx and cassandra/serializers.pxd implementing Cython-optimized serialization that mirrors the deserializers.pyx architecture. Implements type-specialized serializers for the three subtypes commonly used in vector columns: - SerFloatType: 4-byte big-endian IEEE 754 float - SerDoubleType: 8-byte big-endian double - SerInt32Type: 4-byte big-endian signed int32 SerVectorType pre-allocates a contiguous buffer and uses C-level byte swapping for float/double/int32 vectors, with a generic fallback for other subtypes. GenericSerializer delegates to the Python-level cqltype.serialize() classmethod. Factory functions find_serializer() and make_serializers() allow easy lookup and batch creation of serializers for column types. Benchmarks show ~30x speedup over the current io.BytesIO baseline and ~3x speedup over Python struct.pack for Vector<float, 1536> serialization. No setup.py changes needed - the existing cassandra/*.pyx glob already picks up new .pyx files. Also, following review: - Drop the unrelated obj_array() empty-input guard from cassandra/deserializers.pyx. ParseDesc.deserializers is a typed `Deserializer[::1]` memoryview assigned unconditionally in ParseDesc.__init__, so an empty list would still crash there regardless of what obj_array() returns -- the guard didn't fix anything reachable, and this PR doesn't otherwise touch deserialization. - Clarify the docstring on serializers.pyx's own (still present, and directly used/tested) obj_array() empty-input guard so it documents that it is defensive only, and does not by itself make an empty-input call safe end-to-end for a hypothetical future caller that assigns the result to a typed ``Serializer[::1]`` memoryview. - Add a regression test locking in that Vector<smallint> stays on the variable-length (vint-length-prefixed) generic fallback rather than being treated as fixed-width: ShortType.serial_size() correctly returns None (no override), matching real Cassandra wire behavior where smallint vector elements are vint-prefixed, not fixed 2-byte values. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

Add a buffer fast-path to SerVectorType for float32/float64/int32 NumPy arrays: bind the input directly as a typed memoryview and byte-swap in place, skipping per-element Python object creation/indexing entirely. Also, following review: - Fix tests/unit/cython/test_serializers.py importing numpy unconditionally at module scope, which would break test collection for the whole file in a Cython-without-numpy environment (numpy is a dev/test dependency, not a hard runtime requirement). Import numpy lazily inside the numpy-only tests and gate them with the shared `numpytest` skip decorator instead of the unconditional module-level import. - Add regression tests for the `buf_size == 0` guard in each buffer fast-path (float/double/int32), using zero-dimension NumPy arrays, so the empty-memoryview-dereference guard doesn't regress silently. Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

coderabbitai · 2026-07-29T20:39:20Z

Important

Review skipped

Draft detected.

Please check the settings in the CodeRabbit UI or the .coderabbit.yaml file in this repository. To trigger a single review, invoke the @coderabbitai review command.

⚙️ Run configuration

Configuration used: Organization UI

Review profile: CHILL

Plan: Pro Plus

Run ID: 6aee1db4-be72-4952-8cc0-421a41187a08

You can disable this status message by setting the reviews.review_status to false in the CodeRabbit configuration file.

Use the checkbox below for a quick retry:

🔍 Trigger review

_{Comment @coderabbitai help to get the list of available commands.}

mykaul · 2026-07-29T20:43:30Z

Rebased onto latest origin/master and audited this PR against the findings from #749 (which has this PR's two commits stacked underneath it, same pattern as #790/#791).

Fast-path gating — not applicable here: this PR only introduces the cassandra/serializers.pyx module (find_serializer() / make_serializers()); it never wires it into BoundStatement.bind() or PreparedStatement._serializers. That integration, and the fast-path gating fix for scalar-only statements, lives entirely in #749's cassandra/query.py.

Buffer bounds safety — audited the three _serialize_{float,double,int32}_buffer() methods. Cython bounds-checking is not disabled in this file (no @cython.boundscheck(False), unlike numpy_parser.pyx), and buffer size/loop bound both derive from the same validated vector_size used for the length check, so there's no reachable out-of-bounds path. Added regression tests for the buf_size == 0 guard (zero-dimension vectors) in each buffer path.

ShortType/smallint — not hardcoded as fixed-width: serializers.pyx only special-cases FloatType/DoubleType/Int32Type; ShortType has no serial_size() override in this codebase, so it correctly falls back to the generic vint-prefixed path. Added a regression test locking this in.

Also cleaned up two smaller issues found during the audit:

Reverted an unrelated, dead-code obj_array() empty-input guard this PR had added to cassandra/deserializers.pyx — ParseDesc.deserializers is a typed memoryview assigned unconditionally, so the guard never prevented a crash for its one real caller. Clarified the docstring on the equivalent (still-used) guard in serializers.pyx's own obj_array() instead.
Fixed tests/unit/cython/test_serializers.py importing numpy unconditionally at module scope, which would break test collection for the whole file in a Cython-without-numpy environment. Numpy-dependent tests now use the shared numpytest skip decorator with lazy imports.

All prior review threads were already resolved. Rebuilt the Cython extensions from scratch and ran tests/unit/cython/test_serializers.py (83 passed) plus the full tests/unit/ suite (846 passed, 45 skipped, 0 failed). Amended both existing commits (no new commits) and force-pushed.

Restore serializers.pyx/pxd from the PR scylladb#748 branch and add SerDateType that serializes datetime/date/numeric values to 8-byte big-endian int64 millisecond timestamps entirely in C, avoiding Python-level struct.pack. Uses the same timedelta arithmetic as the pure-Python DateType.serialize (Item B) but with C-level int64 byte-swapping. Benchmark shows ~1.5x speedup over the already-optimized Python path for datetime serialization (253 ns vs 381 ns per call).

Copilot

Pull request overview

Copilot reviewed 3 out of 3 changed files in this pull request and generated 1 comment.

Comments suppressed due to low confidence (5)

cassandra/serializers.pyx:554

make_serializers() is documented to return an object-array / typed-memoryview style container, but for empty input obj_array() returns a plain Python list. This makes the return type value-dependent, which can break callers that always treat the result as a memoryview (especially in Cython code). Prefer returning a consistent type: either (a) always return a Python list from make_serializers() (and adjust docs/tests accordingly), or (b) return a zero-length object[:] memoryview by allocating a minimal array and slicing to [:0] (or any other approach that preserves a memoryview type even when empty).

def make_serializers(cqltypes_list):

cassandra/serializers.pyx:563

make_serializers() is documented to return an object-array / typed-memoryview style container, but for empty input obj_array() returns a plain Python list. This makes the return type value-dependent, which can break callers that always treat the result as a memoryview (especially in Cython code). Prefer returning a consistent type: either (a) always return a Python list from make_serializers() (and adjust docs/tests accordingly), or (b) return a zero-length object[:] memoryview by allocating a minimal array and slicing to [:0] (or any other approach that preserves a memoryview type even when empty).

    return obj_array([find_serializer(ct) for ct in cqltypes_list])


def obj_array(list objs):

cassandra/serializers.pyx:583

make_serializers() is documented to return an object-array / typed-memoryview style container, but for empty input obj_array() returns a plain Python list. This makes the return type value-dependent, which can break callers that always treat the result as a memoryview (especially in Cython code). Prefer returning a consistent type: either (a) always return a Python list from make_serializers() (and adjust docs/tests accordingly), or (b) return a zero-length object[:] memoryview by allocating a minimal array and slicing to [:0] (or any other approach that preserves a memoryview type even when empty).

    if not objs:
        return objs
    cdef object[:] arr
    cdef Py_ssize_t i
    arr = cython_array(shape=(len(objs),), itemsize=sizeof(void *), format="O")
    for i, obj in enumerate(objs):
        arr[i] = obj
    return arr

cassandra/serializers.pyx:455

The int32 NumPy fast-path uses int[::1], which binds to C int (platform-dependent width) rather than a guaranteed 32-bit type. Since the serializer is specifically for Int32Type, prefer int32_t[::1] to precisely match the wire type and to avoid any edge-case ABI/platform mismatch. This also makes the intent clearer and keeps the typed-memoryview constraint aligned with the advertised int32-only fast-path.

    cdef inline object _serialize_int32_buffer(self, object values):

cassandra/serializers.pyx:464

The int32 NumPy fast-path uses int[::1], which binds to C int (platform-dependent width) rather than a guaranteed 32-bit type. Since the serializer is specifically for Int32Type, prefer int32_t[::1] to precisely match the wire type and to avoid any edge-case ABI/platform mismatch. This also makes the intent clearer and keeps the typed-memoryview constraint aligned with the advertised int32-only fast-path.

        cdef int[::1] view

+cdef bint is_little_endian
+from cassandra.util import is_little_endian


…nt.bind() When Cython serializers (from cassandra.serializers) are available and no column encryption policy is active, BoundStatement.bind() now uses pre-built Serializer objects cached on the PreparedStatement instead of calling cqltype classmethods. This avoids per-value Python method dispatch overhead and enables the ~30x vector serialization speedup from the Cython serializers module. The bind loop is split into three paths: 1. Column encryption policy path (unchanged behavior) 2. Cython serializers path (new fast path) 3. Plain Python path (no CE, no Cython -- removes per-value ColDesc/CE check) Depends on PR scylladb#748 (Cython serializers module) and PR scylladb#630 (CE-policy bind split).

Restore serializers.pyx/pxd from the PR scylladb#748 branch and add SerDateType that serializes datetime/date/numeric values to 8-byte big-endian int64 millisecond timestamps entirely in C, avoiding Python-level struct.pack. Uses the same timedelta arithmetic as the pure-Python DateType.serialize (Item B) but with C-level int64 byte-swapping. Benchmark shows ~1.5x speedup over the already-optimized Python path for datetime serialization (253 ns vs 381 ns per call).

mykaul mentioned this pull request Mar 14, 2026

(improvement) query: add Cython-aware serializer path in BoundStatement.bind() (1-26x speedup - tens/hundreds of us reduced) #749

Draft

mykaul marked this pull request as draft March 14, 2026 11:23

mykaul requested a review from Copilot March 14, 2026 19:25

Copilot started reviewing on behalf of mykaul March 14, 2026 19:25 View session

Copilot AI reviewed Mar 14, 2026

View reviewed changes

mykaul requested a review from Copilot March 19, 2026 14:19

Copilot AI reviewed Mar 19, 2026

View reviewed changes

mykaul requested a review from Copilot March 24, 2026 22:14

Copilot started reviewing on behalf of mykaul March 24, 2026 22:14 View session

Copilot AI reviewed Mar 24, 2026

View reviewed changes

mykaul force-pushed the perf/cython-serializers branch 2 times, most recently from 91fe2ed to 91cd1ef Compare March 25, 2026 21:43

mykaul requested a review from Copilot March 26, 2026 08:53

Copilot started reviewing on behalf of mykaul March 26, 2026 08:54 View session

Copilot AI reviewed Mar 26, 2026

View reviewed changes

Comment thread cassandra/serializers.pyx Outdated

Comment thread tests/unit/test_serializers.py Outdated

Comment thread tests/unit/test_serializers.py Outdated

Comment thread cassandra/serializers.pyx Outdated

Comment thread cassandra/serializers.pyx

mykaul mentioned this pull request Mar 26, 2026

(fix) tests: fix flaky TestTwistedConnection.test_connection_initialization #767

Merged

mykaul mentioned this pull request Apr 5, 2026

perf: optimize time-series write/read hot paths (10's to 100's of ns savings, 2-25x better) #798

Draft

mykaul changed the title ~~(improvement) serializers: add Cython-optimized serialization for VectorType~~ (improvement) serializers: add Cython-optimized serialization for VectorType (up to 30x faster - 823us -> 4us!) Apr 7, 2026

mykaul force-pushed the perf/cython-serializers branch from c77c7b4 to 97cdad0 Compare April 7, 2026 08:13

mykaul force-pushed the perf/cython-serializers branch from 97cdad0 to de14827 Compare April 7, 2026 09:20

Lorak-mmk force-pushed the master branch from f2a9e87 to 763af09 Compare June 15, 2026 10:57

mykaul and others added 2 commits July 29, 2026 23:36

Copilot AI review requested due to automatic review settings July 29, 2026 20:39

mykaul force-pushed the perf/cython-serializers branch from de14827 to d69ef80 Compare July 29, 2026 20:39

Copilot AI reviewed Jul 29, 2026

View reviewed changes

Comment thread cassandra/serializers.pyx

Comment on lines +39 to +40

cdef bint is_little_endian

from cassandra.util import is_little_endian

Copilot started reviewing on behalf of mykaul July 29, 2026 22:34 View session

		cdef bint is_little_endian
		from cassandra.util import is_little_endian

Uh oh!

Conversation

mykaul commented Mar 14, 2026 • edited Loading Uh oh! There was an error while loading. Please reload this page.

Uh oh!

Summary

What's included

Architecture

Benchmark

List/tuple inputs

NumPy float32 array inputs (buffer fast-path)

End-to-end: NumPy vs Python baseline

Tests

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Reviewed changes

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

Uh oh!

mykaul commented Mar 26, 2026

Uh oh!

coderabbitai Bot commented Jul 29, 2026

Review skipped

Uh oh!

mykaul commented Jul 29, 2026

Uh oh!

Copilot AI left a comment

Choose a reason for hiding this comment

Pull request overview

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

2 participants

mykaul commented Mar 14, 2026 •

edited

Loading