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
8d8a4e0f2b118dc975bbba930aeb7c6cbd623c2a
vLLM
/
vllm
/
v1
/
worker
/
gpu
/
model_states
T
History
Martin Hickey
b2fb83e7ff
[Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (
#50148
)
...
Signed-off-by: Martin Hickey <
martin.hickey@ie.ibm.com
>
2026-07-31 11:20:18 +00:00
..
__init__.py
[ModelRunner V2] Support encoder-only attention (
#49331
)
2026-07-27 00:38:44 +00:00
default.py
[Bugfix] Fix DSA crash under breakable piecewise cudagraphs (
#49302
)
2026-07-21 18:28:13 +01:00
encoder_decoder.py
[Bugfix] Fix multi-modal support on CPU MRV2 (
#50073
)
2026-07-28 06:09:48 +00:00
encoder_only.py
[Attention]: Use KVCacheSpec for AttentionMetadataBuilder type hints (
#50148
)
2026-07-31 11:20:18 +00:00
interface.py
[ModelRunner V2] Support encoder-only attention (
#49331
)
2026-07-27 00:38:44 +00:00
mamba_hybrid.py
[Kernel][Mamba] Fused-kernel support for align-mode DS-conv state migration with num_accepted_tokens > 1 (
#49291
)
2026-07-29 18:54:52 +08:00
mm_pruning.py
[Bugfix][Multimodal] Fix Qwen3-Omni use_audio_in_video with mixed image/video inputs (
#46213
)
2026-07-17 08:31:16 +00:00