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
ca0df1f1227cdd993835a4d2a62861dd3bd2e893
vLLM
/
vllm
/
v1
/
attention
T
History
Wentao Ye
8bdd8d847d
[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (
#57443
)
...
Signed-off-by: yewentao256 <
zhyanwentao@126.com
>
2026-10-02 20:05:27 -04:00
..
backends
[GLM 5.3 Perf] Enable fused multi-step decode, 13.3% E2E throughput improvement for concurrency 1 (
#57443
)
2026-10-02 20:05:27 -04:00
ops
[ROCm][Perf][GLM-5.3-Flash] Add AITER topk backend for decodes (
#58167
)
2026-10-02 11:47:41 +01:00
__init__.py
[V1] Implement vLLM V1 [1/N] (
#9289
)
2024-10-22 01:24:07 -07:00
backend.py
[Misc] Name each backend and its kernel block sizes in block-size errors (
#58557
)
2026-09-28 14:33:18 +08:00
selector.py
[ROCm] Give turboquant boundary layers a layout-compatible backend (
#54988
)
2026-09-23 22:00:07 -05:00