This website requires JavaScript.
Explore
Help
Sign In
karylab_agents
/
vllm
Watch
1
Star
0
Fork
0
forked from
Karylab-cklius/vllm
Code
Pull Requests
2
Actions
1
Packages
Activity
Files
2b84ac669cfd8a4b6433b4ae4505028d9082c3a7
vllm
/
tests
/
models
T
History
Andreas Karatzas
and
GitHub
cef65f0715
[ROCm][CI] Removed hard-coded attn backend requirement for Qwen VL (
#34753
)
...
Signed-off-by: Andreas Karatzas <
akaratza@amd.com
>
2026-02-18 03:59:53 +00:00
..
fixtures
…
language
…
multimodal
[ROCm][CI] Removed hard-coded attn backend requirement for Qwen VL (
#34753
)
2026-02-18 03:59:53 +00:00
quantization
…
__init__.py
…
registry.py
…
test_gguf_download.py
…
test_initialization.py
…
test_oot_registration.py
…
test_registry.py
…
test_terratorch.py
…
test_transformers.py
…
test_utils.py
…
test_vision.py
…
utils.py
[Perf] Optimize grouped topk kernel, 1.2%~2% E2E Throughput improvement (
#32058
)
2026-01-13 10:58:18 -08:00