Martin Pömsl

Set request ID prefix via request header

7

## Description Implement #2292. If a request contains a value for header `x-request-id-prefix`, this string is used as a prefix to the internal request id, which appears in logs and...

Request Prioritization by Header Value

6

### 🚀 The feature Inference requests are stored in a prioritized data structure. The priority of a request can be set via a custom header value. The priority values are...

Request Identification by Header Value

1

### 🚀 The feature Parse an external request id from a custom header value. This request id is used as a prefix to the `TorchServe`-internal request id which occurs in...

Link for pretrained models (including `glove_50_300_2.txt`) down

4

Hi, the Google drive link for the pretrained models file `e2e-coref.tgz` is down (https://drive.google.com/file/d/1fkifqZzdzsOEo0DXMzCFjiNXqsKG_cHi/). This is also the only source of `glove_50_300_2.txt`, which is required for the reproduction of all...

[Bug]: CUDA illegal memory access error when `enable_prefix_caching=True`

9

### Your current environment ```text The output of `python collect_env.py` PyTorch version: 2.3.0+cu121 Is debug build: False CUDA used to build PyTorch: 12.1 ROCM used to build PyTorch: N/A OS:...