423A35C7/LLaMA-Factory
1
0
Fork 0
mirror of https://github.com/hiyouga/LLaMA-Factory.git synced 2025-08-02 03:32:50 +08:00
Code Issues Packages Projects Releases Wiki Activity

[deps] upgrade vllm (#7183)

Browse Source 
Former-commit-id: d739fddb10f51f422c12b1e7d5d7208309bf6c91
This commit is contained in:
hoshi-hiyouga 2025-03-06 15:25:08 +08:00 committed by GitHub
parent 2b21c749c1
commit e7556b591e
4 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

4
README.md
View File

@ -393,7 +393,7 @@ huggingface-cli login
| Mandatory | Minimum | Recommend | | Mandatory | Minimum | Recommend |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| python | 3.9 | 3.10 | | python | 3.9 | 3.10 |
| torch | 1.13.1 | 2.4.0 | | torch | 1.13.1 | 2.5.1 |
| transformers | 4.41.2 | 4.49.0 | | transformers | 4.41.2 | 4.49.0 |
| datasets | 2.16.0 | 3.2.0 | | datasets | 2.16.0 | 3.2.0 |
| accelerate | 0.34.0 | 1.2.1 | | accelerate | 0.34.0 | 1.2.1 |
@ -405,7 +405,7 @@ huggingface-cli login
| CUDA | 11.6 | 12.2 | | CUDA | 11.6 | 12.2 |
| deepspeed | 0.10.0 | 0.16.2 | | deepspeed | 0.10.0 | 0.16.2 |
| bitsandbytes | 0.39.0 | 0.43.1 | | bitsandbytes | 0.39.0 | 0.43.1 |
| vllm | 0.4.3 | 0.7.2 | | vllm | 0.4.3 | 0.7.3 |
| flash-attn | 2.3.0 | 2.7.2 | | flash-attn | 2.3.0 | 2.7.2 |
### Hardware Requirement ### Hardware Requirement

4
README_zh.md
View File

@ -395,7 +395,7 @@ huggingface-cli login
| 必需项 | 至少 | 推荐 | | 必需项 | 至少 | 推荐 |
| ------------ | ------- | --------- | | ------------ | ------- | --------- |
| python | 3.9 | 3.10 | | python | 3.9 | 3.10 |
| torch | 1.13.1 | 2.4.0 | | torch | 1.13.1 | 2.5.1 |
| transformers | 4.41.2 | 4.49.0 | | transformers | 4.41.2 | 4.49.0 |
| datasets | 2.16.0 | 3.2.0 | | datasets | 2.16.0 | 3.2.0 |
| accelerate | 0.34.0 | 1.2.1 | | accelerate | 0.34.0 | 1.2.1 |
@ -407,7 +407,7 @@ huggingface-cli login
| CUDA | 11.6 | 12.2 | | CUDA | 11.6 | 12.2 |
| deepspeed | 0.10.0 | 0.16.2 | | deepspeed | 0.10.0 | 0.16.2 |
| bitsandbytes | 0.39.0 | 0.43.1 | | bitsandbytes | 0.39.0 | 0.43.1 |
| vllm | 0.4.3 | 0.7.2 | | vllm | 0.4.3 | 0.7.3 |
| flash-attn | 2.3.0 | 2.7.2 | | flash-attn | 2.3.0 | 2.7.2 |
### 硬件依赖 ### 硬件依赖

2
setup.py
View File

@ -54,7 +54,7 @@ extra_require = {
"gptq": ["optimum>=1.17.0", "auto-gptq>=0.5.0"], "gptq": ["optimum>=1.17.0", "auto-gptq>=0.5.0"],
"awq": ["autoawq"], "awq": ["autoawq"],
"aqlm": ["aqlm[gpu]>=1.1.0"], "aqlm": ["aqlm[gpu]>=1.1.0"],
"vllm": ["vllm>=0.4.3,<=0.7.2"], "vllm": ["vllm>=0.4.3,<=0.7.3"],
"galore": ["galore-torch"], "galore": ["galore-torch"],
"apollo": ["apollo-torch"], "apollo": ["apollo-torch"],
"badam": ["badam>=1.2.1"], "badam": ["badam>=1.2.1"],

2
src/llamafactory/hparams/parser.py
View File

@ -137,7 +137,7 @@ def _check_extra_dependencies(
check_version("mixture-of-depth>=1.1.6", mandatory=True) check_version("mixture-of-depth>=1.1.6", mandatory=True)
if model_args.infer_backend == "vllm": if model_args.infer_backend == "vllm":
check_version("vllm>=0.4.3,<=0.7.2") check_version("vllm>=0.4.3,<=0.7.3")
check_version("vllm", mandatory=True) check_version("vllm", mandatory=True)
if finetuning_args.use_galore: if finetuning_args.use_galore: