This website requires JavaScript.
Utforska
Hjälp
Logga in
AI
/
amd-strix-halo-vllm-toolboxes
Bevaka
2
Stjärnmärk
0
Förgrening
0
You've already forked amd-strix-halo-vllm-toolboxes
Kod
Ärenden
Pull-förfrågningar
Actions
Packages
Projekt
Släpp
Wiki
Aktiviteter
Files
4d3b046870f1daa0c59700d7ed9856e3c766d4ca
amd-strix-halo-vllm-toolboxes
/
scripts
T
Historik
Donato Capitella
1f96c391fb
feat: Add comprehensive RDMA cluster setup guide, enforce eager mode in cluster benchmarks, and update documentation with cluster details.
2026-02-02 19:34:33 +00:00
..
01-rocm-env-for-triton.sh
updated envs for better strix halo support on vllm
2025-12-19 08:30:02 +00:00
99-toolbox-banner.sh
feat: Introduce vLLM cluster benchmarking and setup scripts, and expand the list of models for local benchmarks.
2026-02-01 15:43:56 +00:00
build_rccl_gfx1151.sh
feat: Introduce custom RCCL library management for gfx1151, including build scripts, Docker integration, and VLLM benchmarks.
2026-02-01 13:23:10 +00:00
cluster_manager.py
feat: Configure ROCm attention via
--attention-backend
CLI argument, disable the Ray dashboard, and make eager mode configurable for cluster benchmarks.
2026-02-02 15:40:16 +00:00
configure_cluster.sh
feat: Add
RAY_DISABLE_METRICS=1
to disable Ray metrics across cluster configurations and scripts.
2026-02-01 21:52:48 +00:00
install_deps.sh
feat: Modularize Dockerfile dependency and ROCm SDK installations into dedicated scripts and add a GitHub Actions workflow to build and consume a custom RCCL library.
2026-02-01 14:50:37 +00:00
install_rocm_sdk.sh
feat: Modularize Dockerfile dependency and ROCm SDK installations into dedicated scripts and add a GitHub Actions workflow to build and consume a custom RCCL library.
2026-02-01 14:50:37 +00:00
manage_rccl_install.sh
feat: Introduce custom RCCL library management for gfx1151, including build scripts, Docker integration, and VLLM benchmarks.
2026-02-01 13:23:10 +00:00
models.py
feat: Optimize model
max_num_seqs
and global benchmark parameters for Strix Halo, and centralize configurations in
models.py
.
2026-02-02 08:45:13 +00:00
start_vllm_cluster.py
feat: Add comprehensive RDMA cluster setup guide, enforce eager mode in cluster benchmarks, and update documentation with cluster details.
2026-02-02 19:34:33 +00:00
start_vllm.py
feat: Configure ROCm attention via
--attention-backend
CLI argument, disable the Ray dashboard, and make eager mode configurable for cluster benchmarks.
2026-02-02 15:40:16 +00:00
zz-venv-last.sh
Updating toolbox and pushing GitHub Action
2025-11-30 14:57:37 +00:00