This website requires JavaScript.
Explore
Help
Sign In
iHore
/
vLLM
Watch
8
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
2
Packages
Projects
Releases
Wiki
Activity
Files
78aa341d124e4e2162defdabde8e8b0a97ffb79d
vLLM
/
vllm
/
v1
/
core
T
History
Aaron Pham
and
Russell Bryant
2fc9075b82
[V1] Structured Outputs + Thinking compatibility (
#16577
)
...
Signed-off-by: Aaron Pham <
contact@aarnphm.xyz
> Co-authored-by: Russell Bryant <
rbryant@redhat.com
>
2025-05-14 15:45:24 -07:00
..
sched
[V1] Structured Outputs + Thinking compatibility (
#16577
)
2025-05-14 15:45:24 -07:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
block_pool.py
[V1][Metrics] add support for kv event publishing (
#16750
)
2025-04-30 07:44:45 -07:00
encoder_cache_manager.py
Enforce valid max_num_batched_tokens when disable_chunked_mm_input=True (
#16447
)
2025-04-11 08:09:52 +00:00
kv_cache_manager.py
[v1][KVCacheManager] pass num_new_computed_tokens to kv cache manager (
#18001
)
2025-05-13 19:09:39 -07:00
kv_cache_utils.py
[Core] Prevent side-channel attacks via cache salting (
#17045
)
2025-04-30 20:27:21 +08:00
single_type_kv_cache_manager.py
[v1][KVCacheManager] Avoid full cache hit by controlling max_length (
#17999
)
2025-05-13 06:50:38 +00:00