This website requires JavaScript.
Explore
Help
Sign In
wassname
/
vllm
Watch
1
Star
0
Fork
0
mirror of
https://github.com/wassname/vllm.git
synced
2026-09-23 13:50:43 +08:00
Code
Issues
Packages
Projects
Releases
Wiki
Activity
Files
cb3b2b9ba4a95c413a879e30e2b8674187519a93
vllm
/
tests
/
core
T
History
Varun Sundar Rabindranath
and
Varun Sundar Rabindranath
cb3b2b9ba4
[Bugfix] Fix incorrect updates to num_computed_tokens in multi-step scheduling (
#9038
)
...
Co-authored-by: Varun Sundar Rabindranath <
varun@neuralmagic.com
>
2024-10-06 12:48:11 -07:00
..
block
[Bugfix] Block manager v2 with preemption and lookahead slots (
#8824
)
2024-09-29 09:17:45 +08:00
__init__.py
[Tests] Add block manager and scheduler tests (
#3108
)
2024-03-05 18:23:34 -08:00
test_block_manager.py
[Performance] Enable chunked prefill and prefix caching together (
#7753
)
2024-08-28 00:36:31 -07:00
test_chunked_prefill_scheduler.py
Fix tests in test_chunked_prefill_scheduler which fail with BlockManager V2 (
#8752
)
2024-09-24 21:26:36 -07:00
test_num_computed_tokens_update.py
[Bugfix] Fix incorrect updates to num_computed_tokens in multi-step scheduling (
#9038
)
2024-10-06 12:48:11 -07:00
test_scheduler_encoder_decoder.py
[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (
#4942
)
2024-08-06 16:51:47 -04:00
test_scheduler.py
Fix test_schedule_swapped_simple in test_scheduler.py (
#8780
)
2024-09-24 21:26:18 -07:00
test_serialization.py
[Core] Optimize SPMD architecture with delta + serialization optimization (
#7109
)
2024-08-18 17:57:20 -07:00
utils.py
[Bugfix] Fix incorrect updates to num_computed_tokens in multi-step scheduling (
#9038
)
2024-10-06 12:48:11 -07:00