Pierrick Hymbert

It should be possible to continusly index and search using [spark streaming](https://spark.apache.org/docs/latest/streaming-programming-guide.html#overview).

PDF Renderer: allow to specify an alternate image or a custom resolution.

13

**Motivation** Input images passed to OCR are often pre-processed (higher resolution, grayed, etc...). It can be useful to specify an alternate image or a lower resolution in renderer, especially for...

server: init functional tests

18

## Motivation Tests has been listed in #4216 as an improvements request. The idea is to ensure all server routes are working properly using the [Gherkin](https://cucumber.io/docs/gherkin/reference/) language to define test...

`quantize`: add imatrix and dataset metadata in GGUF

4

### Context In the context of: - #6656 Add imatrix related metadata in quantum models. ### Changes - quantize: add imatrix n entries, n_chunks, and dataset KV metadata - common:...

### Context Jobs have the source branch instead of the current branch in the concurrency group name: `Canceling since a higher priority waiting request for 'Benchmark-refs/heads/master-' exists` see: - https://github.com/ggerganov/llama.cpp/actions/runs/8752700017...

common: download from URL, improve parallel download progress status

6

### Context When downloading a sharded model, files are downloaded in parallel, it was added in: - #6192 The progressions of each download conflict:  Need to properly implement [CURLOPT_NOPROGRESS](https://curl.se/libcurl/c/CURLOPT_NOPROGRESS.html)...

server: stop generation at `n_ctx_train` if `n_predict` is not set

20

### Context If the model hallucinates (EOS-less generation), server will go to infinite loop if `n_predict` is not set. It is a wrong usage of the server or the model:...

support `--hf-token` param in addition of `--hf-repo`

9

### Motivation Models with non standard licence requires an opt-in on HF and the download requires a read token if the model is gated. ### Proposal - Add an `--hf-token`...