This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
1
Packages
Projects
Releases
Wiki
Activity
Files
fa6ae3117762f12ce9beebf77e255cd1370b6276
vLLM
/
vllm
/
v1
/
core
T
History
Martin Hickey
and
Or Ozeri
cc07dad789
[HMA] [KVEvent] Enable GPU-side KV events for HMA (
#37688
)
...
Signed-off-by: Martin Hickey <
martin.hickey@ie.ibm.com
> Co-authored-by: Or Ozeri <
or@ozery.com
>
2026-04-12 10:01:02 +03:00
..
sched
Fix the order of _free_encoder_inputs (
#38907
)
2026-04-10 22:47:48 -07:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
block_pool.py
[HMA] [KVEvent] Enable GPU-side KV events for HMA (
#37688
)
2026-04-12 10:01:02 +03:00
encoder_cache_manager.py
[Refactor] Move profiling methods to MM budget (
#33559
)
2026-02-02 23:27:00 +08:00
kv_cache_coordinator.py
[BugFix] Avoid prefix cache hit in the same schedule step for mamba layers (
#29387
)
2026-02-10 07:41:16 +00:00
kv_cache_manager.py
[Core] add option to schedule requests based on full ISL (
#37307
)
2026-03-24 13:01:12 -04:00
kv_cache_metrics.py
[Core][Observability] Add KV cache residency metrics (
#27793
)
2025-12-01 18:27:53 +00:00
kv_cache_utils.py
fix: disambiguate multimodal prefix cache keys (
#36708
)
2026-03-20 10:33:20 +08:00
single_type_kv_cache_manager.py
Add Gemma4 Eagle3 support (
#39450
)
2026-04-10 12:35:35 -07:00