Skip to main content

copyengine

Deliver optimal copy performance effortless.

Hand the copies scattered through your code (copy_, gather / scatter, host ↔ GPU transfers, layout changes, casts) to copyengine. It merges them, decides where to reorder and convert, and tunes itself to the hardware it runs on. Existing code mostly stays as it is.

Before / after

# Before: layers × blocks small copies, each its own call (tens of thousands of calls)
for layer in range(L):
    for blk in blocks:
        scale_k[layer][blk].copy_(k_qs_buf[blk].expand(N, S))

# After: one line of wrapping. The loop is unchanged; its copies are merged
# into a few transfers and kernels.
with ce.scope():
    for layer in range(L):
        for blk in blocks:
            scale_k[layer][blk].copy_(k_qs_buf[blk].expand(N, S))

Loops like this are usually rewritten by hand into a few vectorized copies or a custom kernel. copyengine aims to get that result without the rewrite, and without a new kernel for every new model or cache layout.

Where it helps

  • Inference: loading and offloading KV cache blocks between host and GPU, paged caches (gather / scatter by block id), quantizing or dequantizing KV on the way (FP8 or int8 with a scale), swapping LoRA weights in and out.
  • Training: offloading optimizer state and activations, dataloader H2D, checkpoint save / load and resharding (pure reordering).
  • Model code: x.permute(...).contiguous().cuda(), copying after index_select, permute-then-cast: write it as one ce.copy_ into the destination (with ce.lazy for gathers), and it happens in one pass, with the reordering done on the GPU.

copyengine moves and converts data. Computation such as reductions is out of scope: it runs as usual, ordered correctly around the copies.

What it guarantees

  1. Not slower than the original. Wherever torch has the same copy, torch's own copy_ is always a candidate. Anything else is measured against it, including the time copyengine itself spends planning and submitting, and is kept only if it is clearly faster. Decisions keep being re-checked while your program runs. A scope as a whole is held to the same rule: each scope call site compares running intercepted with not intercepting at all (host and GPU time), and stops intercepting where that does not clearly win, for example around ops copyengine does not take (index_copy_) or copies torch already does best (stats()["scopes"]). The explicit API has the same protection where torch can express the copy: ce.lazy views, ce.gather, ce.scatter_, ce.segments and ce.indices are measured against the same copy written with torch ops (indexing, index_copy_, slices) from the same host indices. Conversions with fn= and views torch has no form for (a reversed slice) have no torch equivalent: there copyengine picks the fastest of its own strategies. Either way it cannot beat torch code that does less work, for example indices already on the GPU, and each explicit call costs a few microseconds of host time: for a few small copies per step, freeze() or a CUDA graph is the fast path.
  2. The same results. copyengine only takes a copy when it can produce exactly torch's result; otherwise torch runs it. Host and GPU conversions are bit-identical. (NaN stays NaN, but its sign and payload bits are not kept: torch's own differ between its CPU and CUDA conversions.)
  3. Easy to turn off. CE_DISABLE=1 turns copyengine's choices off: every copy runs through torch's own copy_, or exactly as submitted where torch has no equivalent.
  4. Bounded resources. With torch installed, copyengine's own device memory (staging, copy tables) comes from torch's caching allocator, so it shows in torch.cuda.memory_allocated() and obeys torch's limits; its pinned host buffers come from torch's pinned allocator (the one pin_memory() uses). Device staging has a budget (CE_STAGING_MB), and Engine(max_sms=N) (or CE_MAX_SMS) keeps copy kernels on at most N SMs per GPU, leaving the rest to your compute. Where the driver supports green contexts the limit is hard (checked on start); otherwise copyengine launches at most N thread blocks. DMA copies use the copy engines and no SMs; memory bandwidth is still shared, unless you limit it: ce.scope(bandwidth=8e9) (or Engine(bandwidth=...)) paces the copies on the GPU to about 8 GB/s per direction, leaving the rest of the link to other work.

The first runs of each new copy pattern are a warmup: copyengine measures its options, then locks the fastest. Save the result with eng.save_profile(path) to skip the warmup next time on the same machine.

Install

pip install copyengine

The wheels include the GPU kernels and the torch integration; they use the torch you already have. To build from source instead:

pip install .                      # needs CMake >= 3.26 and a C++20 compiler
                                   # GPU support: CUDA toolkit headers + nvcc at build time
pip install --no-build-isolation . # same, with torch already installed: also builds the torch integration

dtypes: float64/32/16, bfloat16, float8 (e4m3fn, e5m2, e8m0fnu), int64/32/16/8, uint8 and bool convert into each other; packed FP4 (float4_e2m1fn_x2) is copied unconverted.

Requirements: Linux on x86_64 or aarch64 (server ARM such as Grace: GH200, GB200, GB10; not Jetson), Python ≥ 3.10. GPU support runs on CUDA 12.x and 13.x drivers; the driver is loaded at runtime, nothing links against libcuda or cudart.

The torch integration is built against the torch you have installed. If you later switch torch versions, the part that intercepts copy_ is recompiled once on import (needs a C++ compiler, takes seconds, cached). If that is not possible, scopes fall back to a pure-Python interception with the same results, only slower, and a warning says so.

Use torch 2.10 or newer for the best performance. Every torch from 2.9 on gives the same results, but from 2.10 the explicit API (ce.copy_, ce.lazy, ...) runs as a compiled torch op; on 2.9 it goes through Python and costs a few more microseconds per call, which matters for many small copies. scope() interception is compiled on every supported version.

Use

import copyengine as ce
import torch

# 1. Unchanged torch code: copy_ inside a scope is queued and merged.
with ce.scope():
    for l in range(num_layers):
        for i, b in enumerate(block_ids):
            kv_cache[l, b].copy_(host_slot[l, i])

# 2. A copy torch cannot express as one view: gather + permute + cast in one pass.
src = ce.lazy(cache).index_select(0, ids).permute(0, 2, 1, 3)
ce.copy_(out_fp16, src)

# 3. Quantize / dequantize on the way.
ce.copy_(q_int8, x, fn=ce.Elementwise(scale=1 / qs, round=True, clamp=(-127, 127)))

# 4. Ragged or CSR layouts: many segments in one call.
ce.segments(src, dst, src_off, dst_off, length)

# 5. Overlap copies with compute: run them on a copy stream, the host never waits.
with ce.scope(stream="copy") as h:      # or stream=<a torch.cuda.Stream>
    for l in range(num_layers):
        next_kv[l].copy_(host_kv[l, ids])
...                                     # compute keeps running on the current stream
h.wait()                                # the current stream waits for the copies (GPU side)

# 6. A step that runs every iteration with new indices: plan it once.
def load_blocks(caches, pool, block_ids):      # caches: one tensor per layer
    for l, cache in enumerate(caches):
        ce.gather(cache, block_ids, 0, out=pool[l])

step = ce.plan(load_blocks)
step(caches, pool, block_ids)                  # block_ids: a CUDA int64 tensor, new each step

ce.plan(step) (or eng.plan) traces step per argument layout until the engine has settled, then replays its copies without running step or planning. Index arguments are read anew on every call: CUDA int64 tensors directly, and host indices (numpy arrays, lists of ints, CPU integer tensors) when the step passes them straight to ce.gather, ce.scatter_ or ce.lazy(...).index_select (indices the step computes from them are guarded by value instead). For host indices two strategies are measured against each other: DMA descriptors built at each call, and the statement kernel reading the indices on the GPU. Every other tensor the copies touch must be an argument and the same buffer (a new buffer or shape traces again). Only the copies replay, so a step should only copy. A replay is kept only where it beats running step plainly. eng.freeze() / plan.run() replays the last flush exactly (same buffers, same indices).

More: ce.copy_many(dsts, srcs) for lists of copies (one per layer) in one call, ce.gather / ce.scatter_ for index-based copies, ce.barrier() to wait for queued work, ce.probe() to see which copy mechanisms this machine supports (each verified by a real copy). C and C++ callers use include/copyengine/copyengine.h (a stable C ABI) or copyengine::copyengine from CMake.

To see what copyengine did: eng.stats()["last"]["decisions"] lists each group of the last flush with its strategy and why (still exploring, the A/B result it locked on, an online re-check, a CUDA graph capture), and stats()["declined"] counts the intercepted copies it left to torch, by reason. In Nsight Systems every group is an NVTX range named copyengine:<strategy>.

To compare against torch on your GPU: python bench/bench_torch.py.

With an AI coding agent

Two Agent Skills teach coding agents (Claude Code, Codex, Cursor, ...) to adopt and debug copyengine: copyengine-adopt finds copy hotspots, picks the integration, warms it up and proves same results and the measured gain; copyengine-diagnose explains slow, declined or failing copies from copyengine's own stats.

npx skills@1 add https://github.com/itdevwu/copyengine/tree/v0.3.0/skills/copyengine-adopt --global
npx skills@1 add https://github.com/itdevwu/copyengine/tree/v0.3.0/skills/copyengine-diagnose --global

How it works

Copies issued inside a scope are queued instead of run. When the scope ends, copyengine looks at them together: which ones depend on each other (exact address ranges), which can be merged across tensors, and what structure they form (2-D blocks, strides, broadcasts). For each group it picks among merged DMA calls, batched DMA (cuMemcpyBatchAsync), 2-D copies, copy kernels that also cast and scale, moving data densely over the link and reordering it on the GPU, or pinned bounce buffers for pageable memory, and measures which is fastest.

Rules worth knowing

  • Inside a scope, every other op is ordered after the queued copies whose memory it reads or writes, so code in the scope sees the copied data. Memory read without going through torch (.numpy(), raw pointers) needs ce.barrier() first.
  • GPU work runs on the current stream, like torch's own copies. GPU-to-GPU copies are not waited for; intercepted copy_ keeps its non_blocking behavior; the explicit ce.copy_ returns with any host-side copy complete (unless the engine was created with allow_async=True).
  • Threads: ce.scope() and ce.copy_ use a per-thread default engine. An Engine you share between threads works while none of them has a scope open on it; a copy or scope from another thread during one raises an error.
  • Buffers of copies that are not waited for (intercepted non_blocking copies, allow_async) are kept alive until the GPU is done with them.
  • CUDA Graphs: copies inside torch.cuda.graph (scopes, ce.copy_, FrozenPlan.run()) are recorded and replay correctly. Copies torch has no equivalent for must run once before capturing.
  • scope(stream=...): the scope's work (its copies, and any other op written in it) runs on that stream, after what the current stream had queued. The host waits for none of it, even for copies that would otherwise block; the returned handle (wait(), synchronize(), done(), event) orders it against the rest. Its buffers stay alive until the copies are done. Inside a CUDA graph capture this is a fork, and h.wait() the join. Copies copyengine leaves to torch (for example a float-to-int cast) keep torch's own semantics.
  • Index tensors (ce.lazy(...).index_select, ce.gather, ce.scatter_) may be host or CUDA tensors. CUDA indices stay on the GPU: the copy kernel reads them, so the host never waits and new indices reuse the same plan. An out-of-range CUDA index skips that element and raises ValueError at the next synchronize(); duplicate CUDA scatter indices are not detected (undefined, as in torch's index_copy_).
  • Each destination element must be written once per copy: duplicate scatter indices and a source overlapping its own destination raise UnsafeCopy in the explicit API (an intercepted copy_ leaves those to torch).

Environment

Variable Effect
CE_DISABLE=1 turn copyengine's choices off: torch's own copy, or each copy as submitted
CE_EXPLORE=0 never measure: use the loaded profile; copy patterns it does not cover run natively (or with copyengine's default where torch has no equivalent) and are listed in the profile for the next warmup
CE_STAGING_MB device staging budget in MB per stream that stages copies (default 256)
CE_LOG=plan print plans to stderr
CE_SYNC=1 wait for every copy to finish (debugging)
CE_MAX_SMS at most this many SMs per GPU for copy kernels (see guarantee 4)
CE_SHIM=0 skip the compiled copy_ interception; scopes intercept in Python
CE_TORCH_ALLOCATOR=0 take copyengine's device and pinned memory from cuMemAlloc / cuMemHostAlloc instead of torch's allocators
CE_CACHE_DIR where interception builds compiled on import are cached (default ~/.cache/copyengine)

Licensed under Apache-2.0.

Metadata

Release files for copyengine 0.3.0

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for copyengine 0.3.0
File Size Uploaded Provenance Actions
copyengine-0.3.0.tar.gz 213.5 kB With provenance Details for copyengine-0.3.0.tar.gz

Built distributions (wheels)

Table of built distributions (wheels) for copyengine 0.3.0
File Actions
copyengine-0.3.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.12 abi3 Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64 Details for copyengine-0.3.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
copyengine-0.3.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl CPython 3.12 abi3 Linux glibc 2.28+ ARM64, Linux glibc 2.26+ ARM64 Details for copyengine-0.3.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
copyengine-0.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.11 CPython 3.11 Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64 Details for copyengine-0.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
copyengine-0.3.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl CPython 3.11 CPython 3.11 Linux glibc 2.26+ ARM64, Linux glibc 2.28+ ARM64 Details for copyengine-0.3.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
copyengine-0.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl CPython 3.10 CPython 3.10 Linux glibc 2.27+ x86-64, Linux glibc 2.28+ x86-64 Details for copyengine-0.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
copyengine-0.3.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl CPython 3.10 CPython 3.10 Linux glibc 2.26+ ARM64, Linux glibc 2.28+ ARM64 Details for copyengine-0.3.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Total release size: 37.4 MB

Release files / copyengine-0.3.0.tar.gz

Download URL copyengine-0.3.0.tar.gz
Size 213.5 kB
Tags Source
SHA-256 checksum
How to use checksums
7dde73f10e0c7e3098090fb614183de0fd8d6f38b8e5f82db99ad81f26df5e6c
BLAKE2b-256 checksum
How to use checksums
d95fb3523ad18857571bd93167b8cf6d4d16320f1c3ad5be6222f2491624ae33
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL copyengine-0.3.0-cp312-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 6.2 MB
Tags CPython 3.12 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64 abi3
SHA-256 checksum
How to use checksums
e48b5fc99915a0b7356d9a48437eee106b6604e68f50dfc334fc7ab5ad32037a
BLAKE2b-256 checksum
How to use checksums
19386e85d5cdb62fa772098dd5e06a429fd23ab84a565e8144b897f8b4ce1f8f
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL copyengine-0.3.0-cp312-abi3-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size 6.2 MB
Tags CPython 3.12 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64 abi3
SHA-256 checksum
How to use checksums
3eb404d0bdbbf456b0d13c28982977a6d9d6832a5e74571b18f8a1a6db9795a1
BLAKE2b-256 checksum
How to use checksums
8d9a092317e39d2ba1db7945a3a0404175e2cd180ba19eca49753edeb397adbf
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL copyengine-0.3.0-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 6.2 MB
Tags CPython 3.11 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
6de89fb9cdf24acb99bec0846b65a34c0723e052465517fe5644342dadf3ab70
BLAKE2b-256 checksum
How to use checksums
1daed153b67dbd8ef0c95169b7211a82579c8d5084c673714c6020bd848106c6
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL copyengine-0.3.0-cp311-cp311-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size 6.2 MB
Tags CPython 3.11 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64
SHA-256 checksum
How to use checksums
b501380fc276e792f22d9c29bbdd4aae095b1feba3dbd5dea20bffdbecb59c83
BLAKE2b-256 checksum
How to use checksums
bce6cde5ebf0b21d461eaf4fcdbfb25709f3f62984cc60d286665caee2526e56
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl

Download URL copyengine-0.3.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
Size 6.2 MB
Tags CPython 3.10 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64
SHA-256 checksum
How to use checksums
ca3a0d16a5f08001961d0e81eaa8470c1eb364276973f688139a4170cbd83637
BLAKE2b-256 checksum
How to use checksums
82b31560e4dec05ffcdec6596febf32d9ae7004a7a17ca07af109420418944d9
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Release files / copyengine-0.3.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl

Download URL copyengine-0.3.0-cp310-cp310-manylinux_2_26_aarch64.manylinux_2_28_aarch64.whl
Size 6.2 MB
Tags CPython 3.10 Linux glibc 2.26+ ARM64 Linux glibc 2.28+ ARM64
SHA-256 checksum
How to use checksums
4eae9b6d62a171e3b72a3306742a5687111565e7b906b3d2ff02bcf4050cd612
BLAKE2b-256 checksum
How to use checksums
0f69d12bc3feb4d1c3766989ddfdc234dafb44a95f17f9baaee9c8117f611d5d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
Yes
Uploaded via twine/7.0.0 CPython/3.13.16

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

Security for copyengine 0.3.0

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

Full provenance

All 7 files in this release have been uploaded with provenance metadata.

Select from 7 files

Attestation for copyengine-0.3.0.tar.gz

PyPI Publish Attestation

PyPI verified that this artifact, at this checksum, originated from the publisher listed below.

Signed by GitHub Actions, verified by PyPI on Nov 15, 2026.

Transparency log

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.

To learn more about protecting yourself from malicious actors, visit our package security documentation.

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page