badstorm 56bb7b2e43 Force PyTorch's default NCCL process-group timeout in vLLM's ROCm image

2026-08-02 23:03:56 +02:00

..

build-librccl.sh

Add single-node mode, tool/reasoning calling, and TheRock-based RCCL build for vLLM

2026-08-02 12:37:30 +02:00

check-model.py

Standardize llama.cpp env vars and binary handling, add vLLM env passthrough

2026-08-02 18:53:14 +02:00

entrypoint.sh

Standardize llama.cpp env vars and binary handling, add vLLM env passthrough

2026-08-02 18:53:14 +02:00

patch-nccl-default-timeout.py

Force PyTorch's default NCCL process-group timeout in vLLM's ROCm image

2026-08-02 23:03:56 +02:00

rocm-librccl.Containerfile

Add single-node mode, tool/reasoning calling, and TheRock-based RCCL build for vLLM

2026-08-02 12:37:30 +02:00

vllm-rocm.Containerfile

Force PyTorch's default NCCL process-group timeout in vLLM's ROCm image

2026-08-02 23:03:56 +02:00

vllm.caddy

Add single-node mode, tool/reasoning calling, and TheRock-based RCCL build for vLLM

2026-08-02 12:37:30 +02:00

vllm.container

Force PyTorch's default NCCL process-group timeout in vLLM's ROCm image

2026-08-02 23:03:56 +02:00