Yang, Bo

zstd compress serialized decls

3

Summary: Should we unconditionally compress decls (when serializing)? pro: in practice, these are almost always cached somewhere, so it saves space and only requires recompression when a source file changes....

These documents are basically copied from https://hhvm.com/blog/2022/07/12/experimenting-with-nix-github-actions-and-visual-studio-code.html and https://hhvm.com/blog/2022/08/30/experimenting-with-universal-deb-packages.html, with some modification about clang packages. ## Test Plan: Visit http://docs-prod-nix-lb-146144460.us-west-2.elb.amazonaws.com/hhvm/experimental-builds/introduction for preview

Add LibUnwind as a dependency of glog::glog (#101)

1

Summary: X-link: https://github.com/facebookincubator/hsthrift/pull/101 X-link: https://github.com/facebookincubator/katran/pull/172 X-link: https://github.com/facebookincubator/mvfst/pull/273 X-link: https://github.com/fairinternal/AIRStore/pull/38 `LibUnwind` is a dependency of `glog` according to [objdump](https://www.internalfb.com/intern/skycastle/run/117093590319624253/artifact/actionlog.117093590478433674.stdout). This diff adds ${LIBUNWIND_LIBRARY} to the CMake imported library `glog::glog` as an...

Add detailed message for UnauthorizedHTTPError

1

This PR added detailed message for UnauthorizedHTTPError so that people would not be confused when changing the port. See https://github.com/qbittorrent/qBittorrent/issues/8365

Fix typing error due to Optional

3

`Optional` is not a valid type because it needs type parameter # What does this PR do? Fix typing error due to Optional ## Before submitting - [ ] This...

Make B a generic type of Model

1

# What does this PR do? This PR fixes typing error at `def batch_type` ## Before submitting - [ ] This PR fixes a typo or improves the docs (you...

Include health into OpenAPI doc

1

# What does this PR do? Include `/health` into OpenAPI doc ## Before submitting - [x] This PR fixes a typo or improves the docs (you can dismiss the other...

Print error logs from launcher during integration tests

5

# What does this PR do? Print error logs from launcher during integration tests ## Before submitting - [ ] This PR fixes a typo or improves the docs (you...

Support PagedAttention

6

### Feature request [vLLM](https://github.com/vllm-project/vllm) is fast with efficient management of attention key and value memory with PagedAttention, serving higher throughput than TGI. ### Motivation Adopting PagedAttention would increase throughput and...

Guidance acceleration

8

### Feature request [Guidance](https://github.com/microsoft/guidance) can control the generated format, which could be a nice feature if it is built-in - Add extra parameter to `/generate` and `/generate_stream` protocol to specify...