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
ecbfbb8d61cbe1e2dfd63c5a39490e59922fb1b4
vLLM
/
vllm
/
model_executor
/
layers
/
mamba
T
History
Ibrahim Arshad
9853a3c159
fix(gdn): Align prefill warmup with real prefill path (
#39169
)
...
Signed-off-by: Ibrahim Arshad <
38925737+ibrahim1023@users.noreply.github.com
>
2026-04-10 00:49:50 +00:00
..
ops
[Kernel] Mamba support different layout for Conv state (
#37416
)
2026-04-03 01:50:09 +02:00
__init__.py
[Kernel/Model] Migrate mamba_ssm and causal_conv1d kernels to vLLM (
#7651
)
2024-08-28 15:06:52 -07:00
abstract.py
[Model][Spec Decode] Nemotron-H MTP and Mamba Speculative Decoding Support (
#33726
)
2026-02-24 09:49:56 -08:00
gdn_linear_attn.py
fix(gdn): Align prefill warmup with real prefill path (
#39169
)
2026-04-10 00:49:50 +00:00
linear_attn.py
[V0 Deprecation] Refactor kv cache from list to element (
#37487
)
2026-03-23 20:10:11 -07:00
mamba_mixer2.py
[Kernel] Mamba support different layout for Conv state (
#37416
)
2026-04-03 01:50:09 +02:00
mamba_mixer.py
[Kernel] Mamba support different layout for Conv state (
#37416
)
2026-04-03 01:50:09 +02:00
mamba_utils.py
[Kernel] Mamba support different layout for Conv state (
#37416
)
2026-04-03 01:50:09 +02:00
short_conv.py
[Kernel] Mamba support different layout for Conv state (
#37416
)
2026-04-03 01:50:09 +02:00