Damian Kalinowski

Ability to detect client disconnection

12

**Is your feature request related to a problem? Please describe.** In our project we are trying to use Drogon for very long requests (up to 10 minutes long). While it...

Overhead of creating new threads in Streaming Response

7

**Is your feature request related to a problem? Please describe.** There is an overhead of creating new threads when using streaming response feature. This drogon example demonstrates it very well:...

[release branch] Public packages

1

### 🛠 Summary Public official links

[2025.4.1] Gpt-oss multi turn template + add to agentic demo

1

### 🛠 Summary 0.35 BFCL multiturn unary Changes to original chat template: - introducing reasoning=`none` - this automaticly adds empty reasoning channel so it forces the model to skip the...

It fixes issue with openvino-tokenizer support missing for python 3.9 and below, however export_models.py still fails with: ``` Traceback (most recent call last): File "/usr/local/bin/optimum-cli", line 8, in sys.exit(main()) ^^^^^^...

### 🛠 Summary 0.35 BFCL multiturn unary Changes to original chat template: - introducing reasoning=`none` - this automaticly adds empty reasoning channel so it forces the model to skip the...

### 🛠 Summary Changes which are not following OpenAI harmony format, but workaround model accuracy issues - tool call appears in wrong channel (analysis), not only in commentary as supposed...

### 🛠 Summary .bin files can be put directly to benchmark app which is also capable of testing output accuracy as @liubo-intel suggested

### 🛠 Summary CVS-166468