mjolnir-kernel 0.1.0__py3-none-any.whl

mjolnir_kernel-0.1.0.dist-info/METADATA

@@ -0,0 +1,222 @@
+Metadata-Version: 2.5
+Name: mjolnir-kernel
+Version: 0.1.0
+Summary: Mjolnir: a paged decode-attention kernel for NVIDIA Jetson AGX Thor (sm_110) on tcgen05 / TMEM / TMA (CuTe DSL), with fp8 and 6-bit (e2m3) KV caches — packaged as the vLLM MJOLNIR attention backend.
+Project-URL: Homepage, https://github.com/thor-arena/mjolnir
+Project-URL: Documentation, https://github.com/thor-arena/mjolnir/tree/main/docs/kernel
+Project-URL: Repository, https://github.com/thor-arena/mjolnir.git
+Project-URL: Issues, https://github.com/thor-arena/mjolnir/issues
+Project-URL: Changelog, https://github.com/thor-arena/mjolnir/releases
+Author-email: Mieszko Syty <mieszko@ms1design.pl>
+License-Expression: Apache-2.0 AND BSD-3-Clause
+License-File: LICENSE
+License-File: NOTICE
+Keywords: attention,blackwell,cute-dsl,decode,fp8,jetson,sm110,tcgen05,thor,vllm
+Classifier: Development Status :: 4 - Beta
+Classifier: Environment :: GPU :: NVIDIA CUDA
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Operating System :: POSIX :: Linux
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Requires-Python: >=3.10
+Provides-Extra: dsl
+Requires-Dist: nvidia-cutlass-dsl>=4.2; extra == 'dsl'
+Description-Content-Type: text/markdown
+
+# mjolnir-kernel
+
+**Mjolnir** — a paged decode-attention kernel for NVIDIA Jetson AGX Thor
+(`sm_110`, 20 SMs), written in CuTe DSL on Blackwell `tcgen05` tensor cores, and
+packaged as a vLLM attention backend.
+
+```bash
+vllm serve <model> --attention-backend MJOLNIR      # the mjolnir-vllm image
+vllm serve <model> --attention-backend CUSTOM       # stock vLLM 0.31.0 + this package
+```
+
+This package is the kernel only. Serving, calibration and benchmarking are the
+[`mjolnir-cli`](https://pypi.org/project/mjolnir-cli/) package; benchmarks
+(Mjolnir vs FlashInfer vs FlashAttention 2 across context lengths), the design,
+and one chapter per kernel feature live in the project repository:
+**[thor-arena/mjolnir](https://github.com/thor-arena/mjolnir)** — numbers there
+are rendered from the raw results, so they are never stale.
+
+## What it does
+
+The backend subclasses a stock vLLM backend — the *fallback* — and inherits
+its KV-cache allocation, cache write, prefill and validation:
+
+- **on the image**, FlashAttention 4 (`FLASH_ATTN`, resolved to FA4 on sm_110
+  by the image's patch — its prefill is ~40% faster than FlashInfer's on
+  Thor). If FA4's one-time fp8-KV probe fails on the device, the backend logs
+  it and uses FlashInfer instead;
+- **on a stock vLLM**, FlashInfer (stock FA on sm_110 is FA2, which cannot
+  read an fp8 KV cache);
+- `MJOLNIR_ATTN_FALLBACK` picks another either way.
+
+Steps that are **decode only** run on Mjolnir:
+
+- every request has the same `q_len ≤ 1 + num_speculative_tokens` (so MTP /
+  n-gram speculative verification runs on Mjolnir too);
+- CUDA-graph padding requests (zero tokens) may trail the batch;
+- the step is causal — or the non-causal block of a parallel drafter (DSpark,
+  DFlash: every query token sees every key) — and has no cascade prefix.
+
+Every other step (prefill, mixed, cascade) is built and run by the base backend,
+unchanged.
+
+A decode step:
+
+1. **Plan** — an occupancy-pinned split-KV plan (`plan_split_kv`): exactly one
+   wave of 2 CTAs × 20 SMs. The plan lives in persistent device buffers padded to
+   a fixed grid, so full CUDA graphs replay new plans without re-capture.
+2. **Quantize Q** — dynamic e4m3 per `(sequence, KV head)` by default: fp8 Q,
+   fp8 KV and fp8 P go straight into the tensor cores, no conversion warps.
+3. **Stream KV** — TMA loads pages into a shared-memory ring
+   (L2 evict-first: KV is read once), `tcgen05` MMAs accumulate S and O in TMEM,
+   softmax warpgroups run the online softmax.
+4. **Merge** — a small second kernel combines the split-KV partials by LSE.
+
+The KV cache is read through runtime strides: vLLM's `(B,H,N,2D)`, FlashInfer
+NHD/HND, or FlashAttention `(2,B,…)`, uint8 or fp8, with per-tensor or per-head
+scales. Q and O are zero-copy for `q_len == 1`, even as strided views of the
+fused QKV buffer.
+
+## Install
+
+**On the image** (`narandill/mjolnir-vllm:v0.31.0`) it is pre-installed and the
+`MJOLNIR` backend name is patched into vLLM — nothing to do.
+
+**On a stock vLLM 0.31.0** (inside a container that has CUDA 13 and `sm_110`):
+
+```bash
+pip install "mjolnir-kernel[dsl]"          # [dsl] pulls nvidia-cutlass-dsl
+VLLM_KV_CACHE_LAYOUT=HND vllm serve Qwen/Qwen3-8B \
+    --kv-cache-dtype fp8 --attention-backend CUSTOM
+```
+
+The package registers a `vllm.general_plugins` entry point (`mjolnir:register`)
+that maps `AttentionBackendEnum.CUSTOM` — and `MJOLNIR`, when the vLLM build has
+that member — to `mjolnir.backend.MjolnirAttentionBackend` in every vLLM process.
+The two-line enum patch for vLLM is
+[`thor-mjolnir-attention-backend.patch`](https://github.com/thor-arena/mjolnir/blob/main/docker/vllm-thor/patches/thor-mjolnir-attention-backend.patch).
+
+Look for this line in the server log:
+
+```
+Mjolnir decode enabled: h_q=… h_k=… d=… page=… q_len<=… Q=fp8 ctas/SM=2 …
+```
+
+## Requirements
+
+- An fp8 (`fp8` / `fp8_e4m3`) KV cache — or, on the image, a 6-bit
+  `fp6_e2m3` one with calibrated scales (see below); head-major pages
+  (`VLLM_KV_CACHE_LAYOUT=HND`) are fastest.
+- `head_size % 128 == 0`; block size 16, 32, 64 or 128.
+- A bf16 or fp16 model.
+- No sliding window, soft-cap, sinks or ALiBi; no DCP or PCP.
+
+If a layer does not qualify, the builder logs the reason and that KV-cache group
+runs on the fallback backend.
+
+## Configuration
+
+| variable | default | meaning |
+|---|---|---|
+| `MJOLNIR_ATTN_DISABLE` | – | `1`: the plugin does not register; everything runs on the fallback |
+| `MJOLNIR_ATTN_FALLBACK` | `FLASH_ATTN` (FA4) on the image, `FLASHINFER` on stock vLLM | base backend (`FLASHINFER`, `TRITON_ATTN`, …) for prefill and mixed steps |
+| `MJOLNIR_ATTN_Q_DTYPE` | `fp8` | `fp8` (dynamic per-(seq, KV head) quantization) or `bf16` |
+| `MJOLNIR_ATTN_MAX_QLEN` | `1 + num_speculative_tokens` | the largest q_len Mjolnir takes |
+| `MJOLNIR_ATTN_CTAS` | `2` | CTAs per SM (2 is fastest on Thor) |
+| `MJOLNIR_ATTN_MAX_SPLITS` | `16` | max KV chunks per sequence (1 = never split, no merge kernel) |
+| `MJOLNIR_ATTN_KV_STAGES` | `0` | KV ring depth override (0 = the tuned default) |
+| `MJOLNIR_ATTN_PDL` | `0` | `1`: programmatic dependent launch |
+| `MJOLNIR_ATTN_L2_PREFETCH` | `0` | TMA-prefetch K/V this many tiles ahead into L2 |
+| `MJOLNIR_ATTN_KV_EVICT_FIRST` | `1` for fp8 Q, `0` for bf16 Q | L2 evict-first policy on K/V loads |
+| `MJOLNIR_ATTN_PRECOMPILE` | `all` | compile every variant at start-up; `none` compiles on first use |
+| `MJOLNIR_ATTN_KERNEL_CACHE` | on | compiled variants are exported to `$VLLM_CACHE_ROOT/mjolnir/kernels` (else `~/.cache/mjolnir/kernels`) and loaded on the next start instead of recompiling; `0` = off, a path = that directory. Keyed by variant, kernel source, CuTe DSL version and GPU |
+| `MJOLNIR_ATTN_DRAFT_T5` | `1` | `0`: the drafter's layers (MTP / EAGLE) run on the fallback — isolates the draft-step cost (`mjolnir verify profile`). fp8 KV only: refused on fp6 KV, whose fallback cannot be CUDA-graphed |
+| `MJOLNIR_ATTN_NONCAUSAL` | `1` | `0`: a parallel drafter's non-causal block steps (DSpark / DFlash) go to the fallback instead of the decode kernel — fp8 KV only for the same reason as above |
+| `MJOLNIR_ATTN_FUSED_DRAFT` | `1` | `0`: tell vLLM the backend cannot advance draft metadata in place → one graph replay per draft step instead of the fused draft loop |
+| `MJOLNIR_LM_HEAD` | – | `fp8`: quantize the lm_head to e4m3 per row at load, Triton fp8-weight GEMM for the verify and every draft (`mjolnir.lmhead`; config `NVFP4_MJOLNIR_E2M3_LMH8`); the bf16 copy is freed automatically (untied heads only, +2.5 GB KV) |
+| `MJOLNIR_DRAFT_VOCAB` | – | path to a `draft_vocab.json` (`mjolnir calibrate --draft-vocab`): the drafter's logits only over those tokens (VocabTrim); `MJOLNIR_DRAFT_VOCAB_SIZE` keeps the first N (a shorter file is padded with the lowest unused ids, with a warning) |
+ | `MJOLNIR_ATTN_VERBOSE` | – | `1`: print the kernel's compile-time notes (ring stages, TMEM columns) — the standalone harness always does |
+ | `MJOLNIR_ATTN_BANNER` | `1` | `0`: skip the Mjolnir hammer banner in the vLLM boot log (`mjolnir.banner.emit`, once per start, coloured with the server's formatter) |
+| `MJOLNIR_ATTN_KV_LAYOUT` | auto | force the KV view: `BHN2D BNH2D B2NHD B2HND 2BNHD 2BHND` |
+| `MJOLNIR_ATTN_FUSED_QPACK` | `1` | `0`: quantize fp8 Q with PyTorch ops (~10 launches) instead of one Triton kernel |
+| `MJOLNIR_ATTN_KV_SCALES` | – | `fp6_e2m3` KV: the per-(layer, KV head, channel) scales file from `python -m mjolnir.calibrate` |
+| `MJOLNIR_ATTN_KV_SCALE_HEADROOM` | `1.0` | `fp6_e2m3` KV: multiply every calibrated scale |
+| `MJOLNIR_ATTN_KV_CALIBRATE` | – | `1`: record the per-channel amax of every K/V written (what `mjolnir.calibrate` reads) |
+
+The pre-rename `THOR_T5_*` spellings are still honored. Each default is backed
+by a measurement — see the
+[kernel chapters](https://github.com/thor-arena/mjolnir/tree/main/docs/kernel).
+
+## fp6 (e2m3) KV in vLLM
+
+On the image, `--kv-cache-dtype fp6_e2m3` stores K/V as packed 6-bit e2m3
+codes (25% fewer bytes than fp8) with static per-(layer, KV head, channel)
+scales — per channel because K has outlier channels a head-wide scale would
+crush the rest under. Mjolnir writes that cache (`mjolnir/kvfp6.py`), decodes
+from it directly (K's channel scales folded into Q, V's into the output), and
+expands the pages a prefill / mixed step reads to e4m3 for the FA4 fallback
+(channel scales applied, one descale per head). The scales come from a calibration run on fp8 KV:
+
+```bash
+python -m mjolnir.calibrate --config <serve.yaml> --out kv_scales.json   # in the image
+MJOLNIR_ATTN_KV_SCALES=kv_scales.json vllm serve ... --kv-cache-dtype fp6_e2m3 --attention-backend MJOLNIR
+```
+
+(`mjolnir calibrate` / `mjolnir serve` do both for you —
+[docs/faq/fp6-kv.md](https://github.com/thor-arena/mjolnir/blob/main/docs/faq/fp6-kv.md).)
+
+## Beyond fp8: the harness
+
+`mjolnir/t5_decode.py` is the kernel **and** its standalone harness
+(`python -m mjolnir.t5_decode --help`) with a bit-faithful emulator as the
+correctness reference. The harness can also read KV formats vLLM cannot write
+yet — fp6 (`e2m3`/`e3m2`) and fp4 (`e2m1`) read directly by `tcgen05
+kind::f8f6f4`, and `nvfp4` — and defaults to e2m3 on head-major pages for fp8 Q.
+How they compare in speed and accuracy:
+[`kvfmt`](https://github.com/thor-arena/mjolnir/blob/main/docs/kernel/kvfmt.md) and
+[`quant`](https://github.com/thor-arena/mjolnir/blob/main/docs/kernel/quant.md).
+Wiring a vLLM cache-write path for fp6 is an open contribution.
+
+## Tests
+
+From a checkout, on a Thor:
+
+```bash
+mjolnir verify correctness      # kernel vs the emulator, the full case matrix
+mjolnir verify vllm             # runner tests + greedy MJOLNIR-vs-FLASHINFER smoke runs
+```
+
+or directly in the container: `python tests/kernel/test_runner.py`,
+`python tests/kernel/smoke_vllm.py [--eager] [--spec 2]` (they find the package
+installed, via `$MJOLNIR_SRC`, or by walking up to `src/mjolnir`).
+
+Mjolnir rounds P (and, by default, Q) to e4m3, so greedy outputs can flip on
+near-tie tokens and then drift apart — FlashInfer's own greedy output differs
+between CUDA-graph and eager mode. The smoke test therefore compares
+per-step logprobs, not text: the chosen tokens must get the same logprob from
+both backends on the shared prefix, and every divergence must be a near-tie
+(each token in the other's top-5, at most 1 nat apart). The matching prefix
+is printed as information.
+
+## Files
+
+| file | what |
+|---|---|
+| `mjolnir/t5_decode.py` | the CuTe-DSL kernel, the split-KV merge, the harness and the emulator |
+| `mjolnir/runner.py` | plan buffers, compile cache, launch, KV views (no vLLM import) |
+| `mjolnir/backend.py` | the vLLM backend, metadata builder, impl |
+| `mjolnir/__init__.py` | `register()` — the vLLM plugin entry point |
+
+Apache-2.0, except `mjolnir/t5_decode.py`, which is derived from an NVIDIA
+CUTLASS CuTe DSL example and stays under BSD-3-Clause — see `LICENSE` and
+`NOTICE` in this package.

mjolnir_kernel-0.1.0.dist-info/RECORD

@@ -0,0 +1,17 @@
+mjolnir/__init__.py,sha256=Ztl75F0iKUhAN0TV2-TJf5yit6hdkA_VG84oML2eb2o,2700
+mjolnir/backend.py,sha256=YVXqhCJWh33kfRUkE8oVPMbonFV7bLBnAt4ys9Ku0hs,41354
+mjolnir/banner.py,sha256=RBbxZQlQfhDWSL1ESAIOgLwM9fyTjG0sB23gK30qAUM,4572
+mjolnir/calibrate.py,sha256=roMNgpfdT4Q-yOhbPwwRYEozNBTwK1fyHLi71C2pSEE,9325
+mjolnir/draftvocab.py,sha256=4x5zxpvx-sTraE-YAXtbJ-fAGZiI7wixKnB9X0Zx5jg,6759
+mjolnir/kvfp6.py,sha256=bIGpOEil9IMD-BxBYQRnCpF7IeKmd9pkIrECsBkREmo,12587
+mjolnir/kvscales.py,sha256=5KFWVP3ibQDrd0g96804xjxLpibMOkgO9JUxJscZ3ms,6704
+mjolnir/lmhead.py,sha256=DLmbGWFgyVaWe6JHWghMqNbuiaKa756UkYxMkKD1Nts,15670
+mjolnir/qpack.py,sha256=AXtiRmlWUG1y5JCIP6J93ZkqFwXt-tr_FZiN4kq9LJU,4549
+mjolnir/runner.py,sha256=8ESRg5sEtfk25zU5EupevN434JgGb2J02OmZpJXeiCw,30637
+mjolnir/t5_decode.py,sha256=nxz-fk_ODfZwLA8bIxU-qpxYE1PfloplCYsBU12Q-qY,139709
+mjolnir_kernel-0.1.0.dist-info/METADATA,sha256=GrTDaRs1B2CnumjqZE6X7r-wTJEpG0J2pNO_EMjiABc,12540
+mjolnir_kernel-0.1.0.dist-info/WHEEL,sha256=W3fkpkm7-wf9vBI5Z-7s0eWkeM-spu78I8Neb98DeEg,87
+mjolnir_kernel-0.1.0.dist-info/entry_points.txt,sha256=_YTjtsnpuAg-K_0DvumKCu_ySvhUASe2ZJq8XysnyF8,50
+mjolnir_kernel-0.1.0.dist-info/licenses/LICENSE,sha256=z8d0m5b2O9McPEK1xHG_dWgUBT6EfBDz6wA0F7xSPTA,11358
+mjolnir_kernel-0.1.0.dist-info/licenses/NOTICE,sha256=QNkgIhREgHvjziuGKnLtciiWj-Z8P7Dt6jBx6uR4t5U,3733
+mjolnir_kernel-0.1.0.dist-info/RECORD,,

mjolnir_kernel-0.1.0.dist-info/WHEEL

@@ -0,0 +1,4 @@
+Wheel-Version: 1.0
+Generator: hatchling 1.32.4
+Root-Is-Purelib: true
+Tag: py3-none-any

mjolnir_kernel-0.1.0.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[vllm.general_plugins]
+mjolnir = mjolnir:register

mjolnir_kernel-0.1.0.dist-info/licenses/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mjolnir_kernel-0.1.0.dist-info/licenses/NOTICE

@@ -0,0 +1,64 @@
+Mjolnir
+Copyright 2026 Mieszko Syty (ms1design)
+
+This product is licensed under the Apache License, Version 2.0 (see LICENSE),
+except where a file states otherwise. It includes or modifies the third-party
+works listed below; each keeps its own license and copyright notice.
+
+-------------------------------------------------------------------------------
+1. NVIDIA CUTLASS — CuTe DSL examples                         BSD-3-Clause
+-------------------------------------------------------------------------------
+src/mjolnir/mjolnir/t5_decode.py (the Mjolnir decode-attention kernel) is
+derived from
+
+  examples/python/CuTeDSL/cute/blackwell/kernel/attention/mixed_input_fmha/
+  mixed_input_fmha_decode.py
+  https://github.com/NVIDIA/cutlass
+  Copyright (c) 2025 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
+
+The file is distributed under the BSD-3-Clause license, as a whole, with the
+original NVIDIA notice and license text retained at its top; the Mjolnir
+modifications to it are Copyright (c) 2026 Mieszko Syty and are licensed under
+the same BSD-3-Clause terms.
+
+-------------------------------------------------------------------------------
+2. vLLM                                                          Apache-2.0
+-------------------------------------------------------------------------------
+https://github.com/vllm-project/vllm — Copyright the vLLM project contributors.
+
+- docker/vllm-thor/patches/*.patch (except thor-gdn-prefill-fi-sm110.patch)
+  modify vLLM source files; the narandill/mjolnir-vllm image applies them to
+  the vLLM package of the official vllm/vllm-openai image, and marks every file
+  it changes (see docker/vllm-thor/apply_patches.py). Patches 49652, 50885,
+  54165 and 55519 are adapted from the corresponding (unmerged) vLLM pull
+  requests.
+- docker/perses/dashboards/performance_statistics.yaml and
+  query_statistics.yaml are adapted from
+  examples/observability/dashboards/perses/ (changes listed in their headers).
+
+-------------------------------------------------------------------------------
+3. FlashAttention (FA4, CuTe DSL; vendored in vLLM as vllm_flash_attn) BSD-3-Clause
+-------------------------------------------------------------------------------
+https://github.com/Dao-AILab/flash-attention — Copyright (c) Tri Dao and
+contributors. thor-fa4-fp8kv-sm110.patch, thor-fa4-hd256-fp8-sm110.patch and
+thor-fa4-hd256-1cta-decode-sm110.patch modify files of vllm/vllm_flash_attn/
+cute/ (the FlashAttention 4 kernels as vendored by vLLM). The Mjolnir kernel
+itself contains no FlashAttention code; it follows the published
+FlashAttention / FlashDecoding algorithms (online softmax, split-KV + LSE merge).
+
+-------------------------------------------------------------------------------
+4. FlashInfer                                                    Apache-2.0
+-------------------------------------------------------------------------------
+https://github.com/flashinfer-ai/flashinfer — Copyright the FlashInfer
+contributors. thor-gdn-prefill-fi-sm110.patch modifies flashinfer/gdn_prefill.py
+in the image's FlashInfer package.
+
+-------------------------------------------------------------------------------
+The narandill/mjolnir-vllm container image
+-------------------------------------------------------------------------------
+The image is built FROM the official vllm/vllm-openai image and redistributes
+everything in it (vLLM, PyTorch, FlashInfer, NVIDIA CUDA libraries, the
+NVIDIA CUTLASS DSL, Ubuntu packages, ...) under those components' own licenses
+— see the license files inside the image and the upstream projects. It adds
+the mjolnir-kernel package and the patches above; their LICENSE and this
+NOTICE are installed at /usr/share/doc/mjolnir/.