[misc] fix uv (#7913)

.gitignore

@@ -176,3 +176,4 @@ output/
 wandb/
 swanlog/
 generated_predictions.jsonl
+predictions_score.json

README.md

@@ -233,6 +233,9 @@ Compared to ChatGLM's [P-Tuning](https://github.com/THUDM/ChatGLM2-6B/tree/main/
 
 </details>
 
+> [!NOTE]
+> If you cannot use the latest feature, please pull the latest code and install LLaMA-Factory again.
+
 ## Supported Models
 
 | Model                                                             | Model size                       | Template            |
@@ -463,7 +466,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, awq, aqlm, vllm, sglang, galore, apollo, badam, adam-mini, qwen, minicpm_v, modelscope, openmind, swanlab, quality
+Extra dependencies available: torch, torch-npu, metrics, deepspeed, liger-kernel, bitsandbytes, hqq, eetq, gptq, aqlm, vllm, sglang, galore, apollo, badam, adam-mini, qwen, minicpm_v, modelscope, openmind, swanlab, quality
 
 > [!TIP]
 > Use `pip install --no-deps -e .` to resolve package conflicts.

README_zh.md

@@ -236,6 +236,9 @@ https://github.com/user-attachments/assets/43b700c6-a178-41db-b1f8-8190a5d3fcfc
 
 </details>
 
+> [!NOTE]
+> 如果您无法使用最新的功能，请尝试重新拉取代码并再次安装 LLaMA-Factory。
+
 ## 模型
 
 | 模型名                                                             | 参数量                            | Template            |
@@ -466,7 +469,7 @@ cd LLaMA-Factory
 pip install -e ".[torch,metrics]"
 ```
 
-可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、awq、aqlm、vllm、sglang、galore、apollo、badam、adam-mini、qwen、minicpm_v、modelscope、openmind、swanlab、quality
+可选的额外依赖项：torch、torch-npu、metrics、deepspeed、liger-kernel、bitsandbytes、hqq、eetq、gptq、aqlm、vllm、sglang、galore、apollo、badam、adam-mini、qwen、minicpm_v、modelscope、openmind、swanlab、quality
 
 > [!TIP]
 > 遇到包冲突时，可使用 `pip install --no-deps -e .` 解决。

examples/README.md

@@ -195,10 +195,11 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
 
 ### Inferring LoRA Fine-Tuned Models
 
-#### Batch Generation using vLLM Tensor Parallel
+#### Evaluation using vLLM's Multi-GPU Inference
 
 ```
-python scripts/vllm_infer.py --model_name_or_path path_to_merged_model --dataset alpaca_en_demo
+python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
+python scripts/eval_bleu_rouge.py generated_predictions.jsonl
 ```
 
 #### Use CLI ChatBox
@@ -281,9 +282,3 @@ llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
 ```bash
 bash examples/extras/fsdp_qlora/train.sh
 ```
-
-#### Computing BLEU and ROUGE Scores
-
-```bash
-llamafactory-cli train examples/extras/nlg_eval/llama3_lora_predict.yaml
-```

examples/README_zh.md

@@ -195,10 +195,11 @@ llamafactory-cli export examples/merge_lora/llama3_full_sft.yaml
 
 ### 推理 LoRA 模型
 
-#### 使用 vLLM+TP 批量推理
+#### 使用 vLLM 多卡推理评估
 
 ```
-python scripts/vllm_infer.py --model_name_or_path path_to_merged_model --dataset alpaca_en_demo
+python scripts/vllm_infer.py --model_name_or_path meta-llama/Meta-Llama-3-8B-Instruct --template llama3 --dataset alpaca_en_demo
+python scripts/eval_bleu_rouge.py generated_predictions.jsonl
 ```
 
 #### 使用命令行对话框
@@ -281,9 +282,3 @@ llamafactory-cli train examples/extras/llama_pro/llama3_freeze_sft.yaml
 ```bash
 bash examples/extras/fsdp_qlora/train.sh
 ```
-
-#### 计算 BLEU 和 ROUGE 分数
-
-```bash
-llamafactory-cli train examples/extras/nlg_eval/llama3_lora_predict.yaml
-```

pyproject.toml

@@ -88,6 +88,14 @@ conflicts = [
         { extra = "torch-npu" },
         { extra = "vllm" },
     ],
+    [
+        { extra = "torch-npu" },
+        { extra = "sglang" },
+    ],
+    [
+        { extra = "vllm" },
+        { extra = "sglang" },
+    ],
     [
         { extra = "sglang" },
         { extra = "minicpm_v" },

setup.py

@@ -51,9 +51,8 @@ extra_require = {
     "hqq": ["hqq"],
     "eetq": ["eetq"],
     "gptq": ["optimum>=1.17.0", "auto-gptq>=0.5.0"],
-    "awq": ["autoawq"],
     "aqlm": ["aqlm[gpu]>=1.1.0"],
-    "vllm": ["vllm>=0.4.3,<=0.8.4"],
+    "vllm": ["vllm>=0.4.3,<=0.8.5"],
     "sglang": ["sglang[srt]>=0.4.5", "transformers==4.51.1"],
     "galore": ["galore-torch"],
     "apollo": ["apollo-torch"],

src/llamafactory/hparams/parser.py

@@ -148,10 +148,10 @@ def _check_extra_dependencies(
         check_version("mixture-of-depth>=1.1.6", mandatory=True)
 
     if model_args.infer_backend == EngineName.VLLM:
-        check_version("vllm>=0.4.3,<=0.8.4")
+        check_version("vllm>=0.4.3,<=0.8.5")
         check_version("vllm", mandatory=True)
     elif model_args.infer_backend == EngineName.SGLANG:
-        check_version("sglang>=0.4.4")
+        check_version("sglang>=0.4.5")
         check_version("sglang", mandatory=True)
 
     if finetuning_args.use_galore: