A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 9, 17:06 UTC
Auth_token added in documentation as it is required (#32988)
Signed-off-by: Michael Goin <mgoin64@gmail.com> Co-authored-by: Michael Goin <mgoin64@gmail.com>
ruizcrp committed
Jan 24, 2026 at 04:03 UTC
c0d820457a55ec4054f6658b46b0745f6dc2807a
1 file changed
+2
docs/serving/integrations/claude_code.md
+2
@@ -39,6 +39,7 @@ Launch Claude Code with environment variables pointing to your vLLM server:
39
```bash
40
ANTHROPIC_BASE_URL=http://localhost:8000 \
41
ANTHROPIC_API_KEY=dummy \
42
+ANTHROPIC_AUTH_TOKEN=dummy \
43
ANTHROPIC_DEFAULT_OPUS_MODEL=my-model \
44
ANTHROPIC_DEFAULT_SONNET_MODEL=my-model \
45
ANTHROPIC_DEFAULT_HAIKU_MODEL=my-model \
@@ -51,6 +52,7 @@ The environment variables:
52
| -------------------------------- | --------------------------------------------------------------------- |
53
| `ANTHROPIC_BASE_URL` | Points to your vLLM server (default port is 8000) |
54
| `ANTHROPIC_API_KEY` | Can be any value since vLLM doesn't require authentication by default |
55
+| `ANTHROPIC_AUTH_TOKEN` | Is required. Can be any value. |
56
| `ANTHROPIC_DEFAULT_OPUS_MODEL` | Model name for Opus-tier requests |
57
| `ANTHROPIC_DEFAULT_SONNET_MODEL` | Model name for Sonnet-tier requests |
58
| `ANTHROPIC_DEFAULT_HAIKU_MODEL` | Model name for Haiku-tier requests |