This website requires JavaScript.
Esplora
Aiuto
Accedi
AI
/
amd-strix-halo-vllm-toolboxes
Segui
2
Vota
0
Forka
0
Hai già fatto il fork di amd-strix-halo-vllm-toolboxes
Codice
Problemi
Pull Request
Actions
Pacchetti
Progetti
Rilasci
Wiki
Attività
Files
0109e6a19b746c2292fa63a7732c9d974e4bf727
amd-strix-halo-vllm-toolboxes
/
scripts
T
Cronologia
Donato Capitella
0109e6a19b
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
..
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: Update ROCm benchmark result paths, improve cluster node discovery and cache clearing, and refine cluster benchmark result directory.
2026-02-02 07:35:50 +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
refactor: Centralize Ray/vLLM cluster management into a new
cluster_manager.py
module and refactor
start_vllm_cluster.py
to use it.
2026-02-01 22:19:34 +00:00
start_vllm.py
feat: centralize model configurations and benchmark settings into a new
models.py
module and update Dockerfile and scripts to use it.
2026-02-01 21:17:15 +00:00
zz-venv-last.sh
Updating toolbox and pushing GitHub Action
2025-11-30 14:57:37 +00:00