From c4570bcb48011e4f1e05fa1ff91c43b6aab0b9bf Mon Sep 17 00:00:00 2001 From: Yuan Tang Date: Fri, 18 Apr 2025 08:47:47 -0400 Subject: [PATCH] docs: Add tips for debugging remote vLLM provider (#1992) # What does this PR do? This is helpful when debugging issues with vLLM + Llama Stack after this PR https://github.com/vllm-project/vllm/pull/15593 --------- Signed-off-by: Yuan Tang --- docs/source/distributions/self_hosted_distro/remote-vllm.md | 2 +- llama_stack/templates/remote-vllm/doc_template.md | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/source/distributions/self_hosted_distro/remote-vllm.md b/docs/source/distributions/self_hosted_distro/remote-vllm.md index efa443778..46df56008 100644 --- a/docs/source/distributions/self_hosted_distro/remote-vllm.md +++ b/docs/source/distributions/self_hosted_distro/remote-vllm.md @@ -44,7 +44,7 @@ The following environment variables can be configured: In the following sections, we'll use AMD, NVIDIA or Intel GPUs to serve as hardware accelerators for the vLLM server, which acts as both the LLM inference provider and the safety provider. Note that vLLM also [supports many other hardware accelerators](https://docs.vllm.ai/en/latest/getting_started/installation.html) and -that we only use GPUs here for demonstration purposes. +that we only use GPUs here for demonstration purposes. Note that if you run into issues, you can include the environment variable `--env VLLM_DEBUG_LOG_API_SERVER_RESPONSE=true` (available in vLLM v0.8.3 and above) in the `docker run` command to enable log response from API server for debugging. ### Setting up vLLM server on AMD GPU diff --git a/llama_stack/templates/remote-vllm/doc_template.md b/llama_stack/templates/remote-vllm/doc_template.md index fe50e9d49..3cede6080 100644 --- a/llama_stack/templates/remote-vllm/doc_template.md +++ b/llama_stack/templates/remote-vllm/doc_template.md @@ -31,7 +31,7 @@ The following environment variables can be configured: In the following sections, we'll use AMD, NVIDIA or Intel GPUs to serve as hardware accelerators for the vLLM server, which acts as both the LLM inference provider and the safety provider. Note that vLLM also [supports many other hardware accelerators](https://docs.vllm.ai/en/latest/getting_started/installation.html) and -that we only use GPUs here for demonstration purposes. +that we only use GPUs here for demonstration purposes. Note that if you run into issues, you can include the environment variable `--env VLLM_DEBUG_LOG_API_SERVER_RESPONSE=true` (available in vLLM v0.8.3 and above) in the `docker run` command to enable log response from API server for debugging. ### Setting up vLLM server on AMD GPU