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
b0f4866a77f22720a5e295cbcffee5cbe9fc2b56
vLLM
/
vllm
/
platforms
T
History
Wentao Ye
17eb25e327
[Perf] Enable cuda graph for deepepHT, 5.3% throughput improvement, 4.4% TTFT improvement (
#29558
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2025-12-07 04:44:50 +00:00
..
__init__.py
[TPU] Rename path to tpu platform (
#28452
)
2025-11-11 19:16:47 +00:00
cpu.py
[Bugfix][CPU] Fix CPU KV cache fallback memory allocation (
#29604
)
2025-12-04 13:01:15 +08:00
cuda.py
[Perf] Enable cuda graph for deepepHT, 5.3% throughput improvement, 4.4% TTFT improvement (
#29558
)
2025-12-07 04:44:50 +00:00
interface.py
[Attention] Update attention imports (
#29540
)
2025-11-27 11:19:09 -05:00
rocm.py
[PCP&DCP] move CUDAGraph check for PCP&DCP to the check func of platforms (
#29952
)
2025-12-04 21:40:51 -05:00
tpu.py
[Attention] Update attention imports (
#29540
)
2025-11-27 11:19:09 -05:00
xpu.py
[Attention] Update attention imports (
#29540
)
2025-11-27 11:19:09 -05:00