From de5e38e185478960f491a20c6f91934258fabbf6 Mon Sep 17 00:00:00 2001
From: Alfred <massif0601@gmail.com>
Date: Mon, 1 Dec 2025 01:49:43 +0800
Subject: [PATCH] fix: correct typos and bugs in documentation and scripts

- README.md: Fix typo 'vllm-cl' -> 'vllm-cli' in Basic Usage section
- Makefile: Add missing targets to .PHONY declaration (test-cov, format-check, type-check, ci-local, ci-matrix, pre-commit)
- scripts/test_ci_locally.sh: Fix pytest-cov detection using Python import instead of shell command
- scripts/test_ci_locally.sh: Add Python 3.11+ tomllib compatibility for pyproject.toml validation
- docs/profiles.md: Fix grammar 'defaults configuration' -> 'default configuration'
- docs/profiles.md: Update VLLM_ATTENTION_BACKEND value to match actual profile usage
---
 Makefile                   |  2 +-
 README.md                  |  2 +-
 docs/profiles.md           |  4 ++--
 scripts/test_ci_locally.sh | 15 +++++++++++++--
 4 files changed, 17 insertions(+), 6 deletions(-)

diff --git a/Makefile b/Makefile
index fc67ebb..7386a53 100644
--- a/Makefile
+++ b/Makefile
@@ -1,4 +1,4 @@
-.PHONY: help test lint format clean install ci-test all
+.PHONY: help test test-cov lint format format-check type-check clean install ci-test ci-local ci-matrix all pre-commit
 
 # Default target
 help:
diff --git a/README.md b/README.md
index 75716a6..4fc6b44 100644
--- a/README.md
+++ b/README.md
@@ -132,7 +132,7 @@ pipx install --pip-args="--pre" "vllm-cli[vllm]"
 
 ```bash
 # Interactive mode - menu-driven interface
-vllm-cl
+vllm-cli
 # Serve a model
 vllm-cli serve --model openai/gpt-oss-20b
 
diff --git a/docs/profiles.md b/docs/profiles.md
index 0fbf19d..d8a1ed0 100644
--- a/docs/profiles.md
+++ b/docs/profiles.md
@@ -5,7 +5,7 @@ Seven carefully designed profiles cover most common use cases and hardware confi
 ## General Purpose Profiles
 
 ### `standard` - Minimal configuration with smart defaults
-Uses vLLM's defaults configuration. Perfect for most models and hardware setups.
+Uses vLLM's default configuration. Perfect for most models and hardware setups.
 
 **Use Case:** Starting point for any model, general inference tasks
 **Configuration:** No additional arguments - uses vLLM defaults
@@ -182,7 +182,7 @@ Common environment variables used in profiles:
 
 | Variable | Purpose | Values |
 |----------|---------|---------|
-| `VLLM_ATTENTION_BACKEND` | Attention computation backend | `FLASH_ATTN`, `XFORMERS`, `TRITON` |
+| `VLLM_ATTENTION_BACKEND` | Attention computation backend | `FLASH_ATTN`, `XFORMERS`, `TRITON_ATTN_VLLM_V1` |
 | `VLLM_USE_TRITON_FLASH_ATTN` | Enable Triton flash attention | `0`, `1` |
 | `VLLM_ENABLE_FUSED_MOE_ACTIVATION_CHUNKING` | MoE activation chunking | `0`, `1` |
 | `VLLM_USE_FLASHINFER_MXFP4_BF16_MOE` | BF16 precision for MoE | `0`, `1` |
diff --git a/scripts/test_ci_locally.sh b/scripts/test_ci_locally.sh
index b3eb71a..c23a195 100755
--- a/scripts/test_ci_locally.sh
+++ b/scripts/test_ci_locally.sh
@@ -51,8 +51,10 @@ fi
 run_test "Unit Tests" "pytest tests/ -v --tb=short"
 
 # 4. Check Test Coverage (optional but informative)
-if command -v pytest-cov &> /dev/null; then
+if python -c "import pytest_cov" 2>/dev/null; then
     run_test "Test Coverage" "pytest tests/ --cov=src/vllm_cli --cov-report=term-missing --cov-fail-under=50"
+else
+    echo -e "${YELLOW}⚠️  Skipping coverage (pytest-cov not installed)${NC}\n"
 fi
 
 # 5. Linting with flake8
@@ -90,7 +92,16 @@ run_test "CLI Help Test" "python -m vllm_cli --help > /dev/null"
 
 # 12. Validate pyproject.toml
 if [ -f "pyproject.toml" ]; then
-    run_test "Validate pyproject.toml" "python -c 'import toml; toml.load(\"pyproject.toml\"); print(\"pyproject.toml is valid\")'"
+    run_test "Validate pyproject.toml" "python -c '
+try:
+    import tomllib
+    with open(\"pyproject.toml\", \"rb\") as f:
+        tomllib.load(f)
+except ImportError:
+    import toml
+    toml.load(\"pyproject.toml\")
+print(\"pyproject.toml is valid\")
+'"
 fi
 
 # Summary