GitLab

Removing the block manager v1. This is the initial piece of prefix-caching-centric design. In order to achieve prefix-caching-centric design, we need to simplify the code path so that we only use v2 block manager (which has much higher performance on prefix caching).

[Core] Add an environment variable which needs to be set explicitly to allow BlockSpaceManagerV1 (#9149)

Co-authored-by: Varun Sundar Rabindranath <varun@neuralmagic.com>

Co-authored-by: Alexander Matveev <alexm@neuralmagic.com>

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)
Co-authored-by: Andrew Feldman <afeld2012@gmail.com>
Co-authored-by: Nick Hill <nickhill@us.ibm.com>

Co-authored-by: Antoni Baum <antoni.baum@protonmail.com>

Signed-off-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Lei Wen <wenlei03@qiyi.com>

[Core] Cross-attention KV caching and memory-management (towards eventual encoder/decoder model support) (#4837)

Co-authored-by: Roger Wang <ywang@roblox.com>

Co-authored-by: Ruth Evans <ruthevans@Ruths-MacBook-Pro.local>

Co-authored-by: Lei Wen <wenlei03@qiyi.com>

Co-authored-by: Robert Shaw <114415538+robertgshaw2-neuralmagic@users.noreply.github.com>

Since #4335 was merged, I've noticed that the definition of ServerRunner in the tests is the same as in the test for OpenAI API. I have moved the class to the test utilities to avoid code duplication. (Although it only has been repeated twice so far, I will add another similar test suite in #4200 which would duplicate the code a third time)

Also, I have moved the test utilities file (test_utils.py) to under the test directory (tests/utils.py), since none of its code is actually used in the main package. Note that I have added __init__.py to each test subpackage and updated the ray.init() call in the test utilities file in order to relative import tests/utils.py.

Co-authored-by: Lei Wen <wenlei03@qiyi.com>
Co-authored-by: Sage Moore <sagemoore@utexas.edu>