kvcache-ai/Mooncake

Fork

You've already forked Mooncake

mirror of https://github.com/kvcache-ai/Mooncake.git synced 2026-11-05 01:17:55 +00:00

Code Issues 368 Projects Packages Wiki Activity

[PR #1154] [MERGED] Improve AMD HIP support with hipify-perl #2042

New issue

Closed

opened 2026-10-29 21:32:19 +00:00 by bsakaguchi · 0 comments

bsakaguchi commented

2026-10-29 21:32:19 +00:00

Owner

Copy link

📋 Pull Request Information

Original PR: https://github.com/kvcache-ai/Mooncake/pull/1154
Author: @amd-arozanov
Created: 12/2/2025
Status: ✅ Merged
Merged: 12/5/2025
Merged by: @stmatengss

Base: main ← Head: perl_hipify

📝 Commits (6)

4a381ab Improve AMD HIP support with hipify-perl
c36d0a0 [TE] Add HIP support to nvlink-allocator with hipcc compilation
87d78ec Add USE_HIP to the documentation
a6d837e [TE/NVLINK] Check CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_FABRIC_SUPPORTED only if USE_CUDA
4a6a86a [TE/EXAMPLE] Fix compiler error if USE_MNNVL and USE_HIP
c8ff0e2 Address review comments

📊 Changes

20 files changed (+188 additions, -128 deletions)

View changed files

📝 doc/en/build.md (+1 -0)
📝 docs/source/getting_started/build.md (+1 -0)
📝 mooncake-common/common.cmake (+40 -16)
📝 mooncake-p2p-store/build.sh (+4 -0)
📝 mooncake-transfer-engine/example/CMakeLists.txt (+18 -8)
📝 mooncake-transfer-engine/example/transfer_engine_bench.cpp (+4 -4)
📝 mooncake-transfer-engine/example/transfer_engine_bench_with_notify.cpp (+7 -7)
📝 mooncake-transfer-engine/example/transfer_engine_validator.cpp (+4 -5)
📝 mooncake-transfer-engine/include/cuda_alike.h (+1 -0)
📝 mooncake-transfer-engine/include/gpu_vendor/hip.h (+16 -64)
📝 mooncake-transfer-engine/include/transport/nvlink_transport/nvlink_transport.h (+1 -1)
📝 mooncake-transfer-engine/nvlink-allocator/CMakeLists.txt (+19 -1)
📝 mooncake-transfer-engine/nvlink-allocator/build.sh (+25 -3)
📝 mooncake-transfer-engine/nvlink-allocator/nvlink_allocator.cpp (+1 -2)
📝 mooncake-transfer-engine/src/CMakeLists.txt (+6 -2)
📝 mooncake-transfer-engine/src/transport/nvlink_transport/CMakeLists.txt (+10 -0)
📝 mooncake-transfer-engine/src/transport/nvlink_transport/nvlink_transport.cpp (+3 -2)
📝 mooncake-transfer-engine/src/transport/tcp_transport/CMakeLists.txt (+4 -0)
📝 mooncake-transfer-engine/tests/CMakeLists.txt (+22 -12)
📝 mooncake-transfer-engine/tests/nvlink_transport_test.cpp (+1 -1)

📄 Description

Description

(AI Assist)

This PR improves AMD GPU support by migrating to automated CUDA-to-HIP conversion using hipify-perl.

Key Changes:

Automated CUDA-to-HIP conversion with hipify-perl
- Introduced hipify_files() CMake function that converts CUDA source files to HIP-compatible code at build time
- Eliminates need to manually maintain separate CUDA/HIP macro definitions
- Uses official ROCm tool for proper API mapping and compatibility with ROCm updates
- Limitation: Header files are not automatically converted
HIP support for NVLink transport
HIP support for nvlink-allocator
Compatibility fixes
- Fixed compilation errors in examples when both USE_MNNVL and USE_HIP are enabled
Documentation updates
- Added USE_HIP flag to build documentation

Type of Change

Bug fix
New feature
- Transfer Engine
- Mooncake Store
- Mooncake EP
- Integration
- P2P Store
- Python Wheel
Breaking change
CI/CD
Documentation update
Other

How Has This Been Tested?

Checked build:
cmake .. -DUSE_HIP=ON -DUSE_MNNVL=ON -DUSE_ETCD=ON -DSTORE_USE_ETCD=ON -DUSE_CXL=ON -DUSE_TCP=ON && make -j$(nproc) && make install

Checklist

I have performed a self-review of my own code.
I have updated the documentation.
I have added tests to prove my changes are effective.

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/kvcache-ai/Mooncake/pull/1154 **Author:** [@amd-arozanov](https://github.com/amd-arozanov) **Created:** 12/2/2025 **Status:** ✅ Merged **Merged:** 12/5/2025 **Merged by:** [@stmatengss](https://github.com/stmatengss) **Base:** `main` ← **Head:** `perl_hipify` --- ### 📝 Commits (6) - [`4a381ab`](https://github.com/kvcache-ai/Mooncake/commit/4a381ab40f2755f746b9af2545bc946cff7c247c) Improve AMD HIP support with hipify-perl - [`c36d0a0`](https://github.com/kvcache-ai/Mooncake/commit/c36d0a0865d8da85f5a88f827b2a22c4d4992496) [TE] Add HIP support to nvlink-allocator with hipcc compilation - [`87d78ec`](https://github.com/kvcache-ai/Mooncake/commit/87d78ec91cfb0ea95b50fbe12c19a62e6bf6de45) Add USE_HIP to the documentation - [`a6d837e`](https://github.com/kvcache-ai/Mooncake/commit/a6d837ec9438fbffe5935829f845c5fda0c9e02e) [TE/NVLINK] Check CU_DEVICE_ATTRIBUTE_HANDLE_TYPE_FABRIC_SUPPORTED only if USE_CUDA - [`4a6a86a`](https://github.com/kvcache-ai/Mooncake/commit/4a6a86ae90e3e101341ca4c41461e9bf2deb897c) [TE/EXAMPLE] Fix compiler error if USE_MNNVL and USE_HIP - [`c8ff0e2`](https://github.com/kvcache-ai/Mooncake/commit/c8ff0e28e992b007d9bfc1c598e73783328259dc) Address review comments ### 📊 Changes **20 files changed** (+188 additions, -128 deletions) <details> <summary>View changed files</summary> 📝 `doc/en/build.md` (+1 -0) 📝 `docs/source/getting_started/build.md` (+1 -0) 📝 `mooncake-common/common.cmake` (+40 -16) 📝 `mooncake-p2p-store/build.sh` (+4 -0) 📝 `mooncake-transfer-engine/example/CMakeLists.txt` (+18 -8) 📝 `mooncake-transfer-engine/example/transfer_engine_bench.cpp` (+4 -4) 📝 `mooncake-transfer-engine/example/transfer_engine_bench_with_notify.cpp` (+7 -7) 📝 `mooncake-transfer-engine/example/transfer_engine_validator.cpp` (+4 -5) 📝 `mooncake-transfer-engine/include/cuda_alike.h` (+1 -0) 📝 `mooncake-transfer-engine/include/gpu_vendor/hip.h` (+16 -64) 📝 `mooncake-transfer-engine/include/transport/nvlink_transport/nvlink_transport.h` (+1 -1) 📝 `mooncake-transfer-engine/nvlink-allocator/CMakeLists.txt` (+19 -1) 📝 `mooncake-transfer-engine/nvlink-allocator/build.sh` (+25 -3) 📝 `mooncake-transfer-engine/nvlink-allocator/nvlink_allocator.cpp` (+1 -2) 📝 `mooncake-transfer-engine/src/CMakeLists.txt` (+6 -2) 📝 `mooncake-transfer-engine/src/transport/nvlink_transport/CMakeLists.txt` (+10 -0) 📝 `mooncake-transfer-engine/src/transport/nvlink_transport/nvlink_transport.cpp` (+3 -2) 📝 `mooncake-transfer-engine/src/transport/tcp_transport/CMakeLists.txt` (+4 -0) 📝 `mooncake-transfer-engine/tests/CMakeLists.txt` (+22 -12) 📝 `mooncake-transfer-engine/tests/nvlink_transport_test.cpp` (+1 -1) </details> ### 📄 Description ## Description *(AI Assist)* This PR improves AMD GPU support by migrating to automated CUDA-to-HIP conversion using `hipify-perl`. **Key Changes:** 1. **Automated CUDA-to-HIP conversion with `hipify-perl`** - Introduced `hipify_files()` CMake function that converts CUDA source files to HIP-compatible code at build time - Eliminates need to manually maintain separate CUDA/HIP macro definitions - Uses official ROCm tool for proper API mapping and compatibility with ROCm updates - **Limitation:** Header files are not automatically converted 2. **HIP support for NVLink transport** 3. **HIP support for nvlink-allocator** 4. **Compatibility fixes** - Fixed compilation errors in examples when both `USE_MNNVL` and `USE_HIP` are enabled 5. **Documentation updates** - Added `USE_HIP` flag to build documentation ## Type of Change - [ ] Bug fix - [x] New feature - [x] Transfer Engine - [ ] Mooncake Store - [ ] Mooncake EP - [ ] Integration - [ ] P2P Store - [ ] Python Wheel - [ ] Breaking change - [ ] CI/CD - [x] Documentation update - [ ] Other ## How Has This Been Tested? 1. Checked build: cmake .. -DUSE_HIP=ON -DUSE_MNNVL=ON -DUSE_ETCD=ON -DSTORE_USE_ETCD=ON -DUSE_CXL=ON -DUSE_TCP=ON && make -j$(nproc) && make install ## Checklist - [x] I have performed a self-review of my own code. - [x] I have updated the documentation. - [x] I have added tests to prove my changes are effective. --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>

bsakaguchi

2026-10-29 21:32:19 +00:00

closed this issue
added the
pull-request
label

No Branch/Tag specified

main

te-coro

staryxchen-tent-capability-research

feature/musa-ep-jit

zxpdemonio/fix-tent-bootstrap-admission

add-store-rs-tone-tests

scatter-rdma-completion-pr2

P2P-Mooncake-Store

release/v0.3.14

feat/tent-rdma-adaptive-adapter

fix/ep-local-counter-gpu-scope

codex/kvcs-oplog-eviction

give-me-a-star

cruz/mooncake-kvcs-lowlevel-pr1-20261008

ylt-handshake-limits

ci/rocm-e2e-tent

sima/docs-pypi-downloads

fix-ci/hicache-mooncake-metadata-loopback

sima/cuda-driver-loading

sima/ci-performance-gate

fix/tent-rdma-unknown-topology-rail-pairing

ci/tent-e2e-dual-job

mc-patch-1

codex/p2p-merge-prerequisites

sima/store-hca-numa-placement

codex/p2p-merge-cli

codex/p2p-merge-ipv6

copilot/fix-ctests-job-failure

czh/pg-device-collectives-pr6

dependabot/cargo/mooncake-store-rs/pyo3-0.29.0

czh/pg-device-collectives-pr5

codex/segment-pool-master-cutover

sima/nightly-ci-recovery

ci/tent-params

stmatengss-patch-1

dependabot/cargo/mooncake-store-rs/rand-0.8.8

dependabot/cargo/mooncake-store-rs/opentelemetry_sdk-0.32.1

dependabot/cargo/mooncake-store-rs/xxhash-rust-0.8.16

codex/migrate-store-rest-service

fix/tone-wheel-arch-selection

czh/pg-device-collectives-pr4

czh/pg-device-collectives-pr3

ketong/fix_moe_tc

copilot/fix-test-wheel-ubuntu-job

fix/ci-wheel-torch-pg-pin

codex/migrate-structured-object-storage

codex/migrate-allocator-python

codex/migrate-vllm-python

codex/migrate-shared-segment

ci/fix_sgl_eval_install

codex/segment-pool-nof-placement-cleanup

feat/pip-native-release

copilot/bugfix-ha-standby-promotion

copilot/mooncake-store-transport-settings

copilot/fix-tensor-support-issues

copilot/optimize-rl-direction

copilot/mooncake-storeagentic-workflow

copilot/fix-client-reconnect-timeout

copilot/mooncake-error-debugging

copilot/mooncake-ipv6-support

feat/nccl-host-python-api

dependabot/go_modules/mooncake-p2p-store/src/p2pstore/google.golang.org/grpc-1.82.1

copilot/migrate-and-move-operations

copilot/migrate-and-move-operations-again

refactor/centralize-env-vars

idhanani/mooncake-retain-groups

copilot/codeownerreviewer

copilot/give-feedback-on-issue-2123

copilot/create-issue-rfc

copilot/break-cuda-monopoly-logic

copilot/compare-cudamemcpy-cu12-cu13

copilot/report-ci-error-issue

copilot/research-commit-history-analysis

copilot/explain-mooncake-store-service

copilot/analyze-project-functionality

copilot/sub-pr-1680

copilot/review-pr-1680

copilot/sub-pr-1597

copilot/fix-github-actions-job-failure

copilot/move-test-sglang-integration-job

v0.3.14

v0.3.14-pre-4

v0.3.14-pre-3

v0.3.14-pre-2

v0.3.14-pre

v0.3.14-rc1

v0.3.13.post1

v0.3.13-rc2

v0.3.13-rc1

v0.3.13

v0.3.12.post1

v0.3.12

v0.3.11-rc1

v0.3.11.post1

v0.3.11

v0.3.10.post2

v0.3.10.post1

v0.3.10

v0.3.9

v0.3.8.post1

v0.3.8

v0.3.7.post2

v0.3.7.post1

v0.3.7

v0.3.6.post1

v0.3.6

v0.3.5

v0.3.4.post2

v0.3.4.post1

v0.3.4

v0.3.3.post2

v0.3.3.post1

v0.3.3

v0.3.2.post1

v0.3.2

v0.3.1

v0.3.0

v0.3.0-beta

v0.3.0-alpha

v0.2.0

Labels

Clear labels

Mirrored from GitHub Pull Request

No labels

Milestone

Clear milestone

No items

No milestone

Projects

Clear projects

No items

No project

Assignees

Clear assignees

No assignees

1 participant

Notifications

Due date

The due date is invalid or out of range. Please use the format "yyyy-mm-dd".

No due date set.

Dependencies

No dependencies set.

Reference

kvcache-ai/Mooncake#2042

Reference in a new issue

Repository

kvcache-ai/Mooncake

Title

Body

No description provided.

Delete branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?

Rows
Columns