lanlin

When using custom model file and building the engine in parallel, the original implementation will raise import error.

镜像名: jax-wheels 上游路径: https://storage.googleapis.com/jax-releases/jax_cuda_releases.html 镜像简介: https://github.com/google/jax 国内其他镜像源同步情况: 同步方法: 镜像大小: 状态追踪: - [ ] 同意同步 - [ ] 同步脚本 - [ ] 部署到镜像源 - [ ] 首次同步成功 - [ ] 测试脚本...

Move Tensorkubes content to separate repository

4

Yesterday, I saw the complete example of tf on k8s. But now some files are missing in the branch ”tensorkubes“. Could you send me the original complete file? thx~

[Bug] Ascend v0.7.2.post1，对serving api测速，概率性卡死

15

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [x] 2. The bug has not been fixed in the latest version. -...

when a model has layers with and without GPT plugin enabled, GptSession raises error

1

### System Info TensorRT-LLM: latest main branch built in the triton-trtllm container (23.12) GPU: V100 ### Who can help? @byshiue ### Information - [ ] The official example scripts -...

env: ``` ms-swift==3.10.0 transformers==4.57.1 ``` I add a print after sleep [here](https://github.com/modelscope/ms-swift/blob/main/swift/trainers/rlhf_trainer/rollout_mixin.py#L170) ``` ... context = self.offload_context if self.enable_offload else nullcontext with context(): self.engine = self._prepare_vllm_engine() if args.sleep_level > 0:...