GitLab

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>

Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>

Signed-off-by: Ryan McCormick <rmccormick@nvidia.com>

Signed-off-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>

feat: enhance GPT OSS frontend with improved harmony tool calling parser and reasoning parser (#2999)
Signed-off-by: zhongdaor <zhongdaor@nvidia.com>

Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>

Signed-off-by: Harrison King Saturley-Hall <hsaturleyhal@nvidia.com>

Co-authored-by: Graham King <grahamk@nvidia.com>

Signed-off-by: Ryan Olson <ryanolson@users.noreply.github.com>

Signed-off-by: Neelay Shah <neelays@nvidia.com>
Co-authored-by: coderabbitai[bot] <136622811+coderabbitai[bot]@users.noreply.github.com>
Co-authored-by: Olga Andreeva <124622579+oandreeva-nv@users.noreply.github.com>

Signed-off-by: Dan Aloni <dan.aloni@vastdata.com>

feat: add a hierarchical Prometheus MetricsRegistry trait for DistributedRuntime, Namespace, Components, and Endpoint (#2008)
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Ryan Olson <rolson@nvidia.com>

Remove http and llmctl binaries. They have been unused for a while.

Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>

Allow both password or TLS auth, if none of these is provided fallback to no auth

Closes #657

New vllm and sglang engines that run in a sub-process. Will hopefully replace the existing embedded python engines.
    
Why?
    
  - Pure Python, does not require knowing Rust to work on it. Much simpler to maintain.
  - No embedded Python interpreter which avoids linking libpython and avoids the MacOS virtualenv issues.
  - Should have better performance as it's "native" vllm / sglang.
  - Works with any version of vllm (including v1!) and sglang. Less upgrade struggle.