image-server-wheels
Prebuilt Python 3.11 wheels.
Contents
| File | OS | CUDA | Torch | Source | Notes |
|---|
ace_step-1.6.0-py3-none-any.whl | any | — | — | built by us | Pure-Python, cross-platform |
qwen_tts-0.1.1+deapi3-py3-none-any.whl | any | — | — | built by us | Pure-Python, patched fork (+deapi3) |
image_server_kernels-0.4.2+cu128torch2.8-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | built by us | Current. Adds Sol-Attn sparse attention, W4A8 linear, and in-tree llama.cpp GGUF CUDA kernels (_C_gguf), on top of: FP8 dense + grouped GEMM, NVFP4 W4A4, INT8 W8A8 + ConvRot, fused QK-norm+RoPE. SM89 + SM120 |
image_server_kernels-0.3.0-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | built by us | Previous build, kept as a fallback. No Sol-Attn, no W4A8, no bundled GGUF kernels |
image_server_kernels-0.3.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl | Linux x86_64 | 12.9 | 2.8 | built by us | Linux build is still at 0.3.0 — there is no Linux 0.4.2 yet |
block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | built by us | Used by video pipeline |
block_sparse_attn-0.0.2-cp311-cp311-linux_x86_64.whl | Linux x86_64 | 12.8 | 2.8 | built by us | Used by video pipeline |
q8_kernels-0.0.5-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | built by us | Used by LTX video |
q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl | Linux x86_64 | 12.8 | 2.8 | built by us | Used by LTX video |
sageattention-2.2.0+cu128torch2.8.0-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | woct0rdho/SageAttention | Mirror of upstream release |
sageattention-2.2.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl | Linux x86_64 | 12.9 | 2.8 | provenance unconfirmed — see Credits | |
flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl | Windows x64 | 12.8 | 2.8 | mjun0812/flash-attention-prebuild-wheels | Mirror of upstream release |
flash_attn-2.8.3+cu130torch2.10-cp311-cp311-win_amd64.whl | Windows x64 | 13.0 | 2.10 | mjun0812/flash-attention-prebuild-wheels | Mirror of upstream release |
flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl | Linux x86_64 | 12.8 | 2.8 | mjun0812/flash-attention-prebuild-wheels | Mirror of upstream release |
Direct install
1BASE=https://huggingface.co/deAPI-ai/image-server-wheels/resolve/main
2
3# Windows
4pip install $BASE/image_server_kernels-0.4.2+cu128torch2.8-cp311-cp311-win_amd64.whl
5pip install $BASE/q8_kernels-0.0.5-cp311-cp311-win_amd64.whl
6pip install $BASE/block_sparse_attn-0.0.2-cp311-cp311-win_amd64.whl
7pip install $BASE/flash_attn-2.8.2+cu128torch2.8-cp311-cp311-win_amd64.whl
8pip install $BASE/sageattention-2.2.0+cu128torch2.8.0-cp311-cp311-win_amd64.whl
9pip install --no-deps $BASE/ace_step-1.6.0-py3-none-any.whl
10pip install --no-deps $BASE/qwen_tts-0.1.1+deapi3-py3-none-any.whl
11
12# Linux
13pip install $BASE/image_server_kernels-0.3.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl
14pip install $BASE/q8_kernels-0.0.5-cp311-cp311-linux_x86_64.whl
15pip install $BASE/block_sparse_attn-0.0.2-cp311-cp311-linux_x86_64.whl
16pip install $BASE/sageattention-2.2.0+cu129torch2.8-cp311-cp311-linux_x86_64.whl
17pip install --no-deps $BASE/flash_attn-2.8.3+cu128torch2.8-cp311-cp311-linux_x86_64.whl
sageattention is required by the MiniMax-H3 video model, which imports it
unconditionally. Every other model that can use it falls back to SDPA when it is
absent, so on a box that does not serve H3 the wheel is optional.
image_server_kernels is at 0.4.2 on Windows but only 0.3.0 on Linux — the
Linux build of 0.4.2 has not been made yet. Sol-Attn, W4A8 and the bundled GGUF
kernels are therefore Windows-only for now.
What is verified in image_server_kernels-0.4.2
Built and tested on Windows 11 / RTX 5090 Laptop (SM120), CUDA 12.8, torch 2.8.0+cu128.
scripts/smoke_test_rebuild.py — ALL PASS: fp8_dense_gemm (per-tensor cos 0.99965,
per-channel+bias 0.99972), dynamic_per_token_scaled_fp8_quant 0.99965,
fp8_dense_gemm_pre_quantized 1.00000, fp8_dense_gemm_sm120 1.00000 via native
CUTLASS 3.x, rmsnorm_forward 0.999999.scripts/validate_gguf_kernels.py against real GGUF tensors — ALL PASS for
Q4_K, Q5_K, Q6_K, Q5_0, Q5_1, Q8_0 (cos 0.99984–1.00000), which covers the bf16
K-quant dequant path the in-tree patch exists for.sol_attn on real MiniMax-H3 activations (S=15,479, 5 capture points):
2.22x vs SageAttention2 at cos 0.9805 at tau=1.0. Both speed and accuracy
rise with sequence length (4k → 1.68x/0.965, 15.5k → 2.90x/0.980 in one run),
so longer clips do better than this figure.
Not exercised on this box: sol_attn on Ada SM89 (compiles and links, but no Ada
GPU here), w4a8_linear, nvfp4_*, fp8_grouped_gemm, w8a16_dense_gemm.
Credits
flash_attn wheels are mirrored from
mjun0812/flash-attention-prebuild-wheels
— all credit for those builds goes to the upstream author.
sageattention is
a mirror, not our build. The library is
thu-ml/SageAttention (Apache-2.0); the
Windows wheel is built and published by
woct0rdho, and we found it
through
wildminder/AI-windows-whl,
which indexes Windows CUDA wheels. All credit for the library and the build goes to
them. The Windows file here is byte-identical to the upstream release
(
sha256:4379951403809dfcd5b1e10d35e287abf42afafb7b27615c09d6062cfbdf230a).
The Linux sageattention-2.2.0+cu129torch2.8 wheel's provenance is not
recorded — we have not confirmed whether it is our own build or a mirror. Fill
this in before relying on the attribution.
We mirror third-party wheels so the install scripts have a single source of truth and
do not break if upstream release URLs change.
ace_step, qwen_tts, image_server_kernels, block_sparse_attn and q8_kernels
were built in-house.
Sol-Attn in image_server_kernels wraps CUDA kernels from comfy-kitchen
(Apache-2.0); see third_party/comfy_kitchen_sol/PROVENANCE.md in the
image-server-kernels repo. The bundled GGUF kernels are llama.cpp's ggml-cuda
(MIT), vendored per third_party/llamacpp_gguf/PROVENANCE.md.
