이 웹사이트는 JavaScript가 필요합니다.
탐색
도움말
로그인
AI
/
amd-strix-halo-vllm-toolboxes
구독
2
별점
0
포크
0
amd-strix-halo-vllm-toolboxes 이미 포크됨
코드
이슈
풀 리퀘스트
액션
패키지
프로젝트
릴리즈
위키
활동
파일
gfx1150
amd-strix-halo-vllm-toolboxes
/
scripts
T
파일 추가
새 파일
파일 업로드
패치 적용
Permalink 복사
디렉토리를 ZIP 이름으로 다운로드
디렉토리를 TAR.GZ 이름으로 다운로드
디렉토리 삭제
히스토리
devbadxyz
48a20990d3
Improve compilation support
2026-03-15 13:04:09 +01:00
..
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
Improve compilation support
2026-03-15 13:04:09 +01:00
build_rccl_gfx1151.sh
Improve compilation support
2026-03-15 13:04:09 +01:00
cluster_manager.py
improve benchmarks
2026-02-25 09:29:46 +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
generate_readme_table.py
feat: Add script to automate README benchmark table generation and update max context benchmarks with new models and a kernel parameter change.
2026-02-02 22:32:12 +00:00
install_deps.sh
Improve compilation support
2026-03-15 13:04:09 +01:00
install_rocm_sdk.sh
Improve compilation support
2026-03-15 13:04:09 +01:00
manage_rccl_install.sh
Improve compilation support
2026-03-15 13:04:09 +01:00
measure_bandwidth.sh
feat: Introduce
measure_bandwidth.sh
script, install
perfquery
, and add the script to the Docker image for RDMA bandwidth monitoring.
2026-02-07 10:40:53 +00:00
models.py
force egaer mode to make gemma stable
2026-02-23 18:19:15 +00:00
patch_strix.py
Improve compilation support
2026-03-15 13:04:09 +01:00
start_vllm_cluster.py
config: Add VLLM_DISABLE_COMPILE_CACHE=1 to environment variables across VLLM scripts.
2026-03-09 14:07:43 +00:00
start_vllm.py
config: Add VLLM_DISABLE_COMPILE_CACHE=1 to environment variables across VLLM scripts.
2026-03-09 14:07:43 +00:00
zz-venv-last.sh
Updating toolbox and pushing GitHub Action
2025-11-30 14:57:37 +00:00