Logo
Explore Help
Sign In
iHore/vLLM
Watch 8
Star 0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
Files
d24cf322e19af19b7a4cbbf108b381b432496f96
vLLM/vllm/platforms
T
History
Zhiyuan Li d24cf322e1 [Hybrid]: Decouple Kernel Block Size from KV Page Size (#24486)
Signed-off-by: lizhiyuan <uniartisan2017@gmail.com>
Signed-off-by: Zhiyuan Li <uniartisan2017@gmail.com>
2025-10-08 23:43:39 -07:00
..
__init__.py
[Bugfix] Fix vllm bench ... on CPU-only head nodes (#25283)
2025-10-08 16:06:42 +00:00
cpu.py
[Frontend] CompilationConfig overhaul (#20283): deprecate use_inductor in favor of backend, simplify custom_ops (#26113)
2025-10-07 12:53:43 -07:00
cuda.py
[Hybrid]: Decouple Kernel Block Size from KV Page Size (#24486)
2025-10-08 23:43:39 -07:00
interface.py
[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)
2025-10-08 20:25:31 +00:00
rocm.py
[Hardware][AMD] Enable FlexAttention backend on ROCm (#26439)
2025-10-09 06:20:18 +00:00
tpu.py
[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)
2025-10-08 20:25:31 +00:00
xpu.py
[Kernel] Centralize platform kernel import in current_platform.import_kernels (#26286)
2025-10-08 20:25:31 +00:00
Powered by Gitea Version: 1.27.2 Page: 47ms Template: 4ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API