Logo
Explore Help
Register Sign In
wassname/vllm
1
0
Fork 0
You've already forked vllm
mirror of https://github.com/wassname/vllm.git synced 2026-07-09 03:15:02 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
3b2005e1db79efe2ea4587035eb2e7ced6e258cb
vllm/csrc/moe
T
History
Yang Chen 95460fc513 [Kernel] port sgl moe_align_block_size kernels (#12574)
sgl_moe_align_block_size is based on:


https://github.com/sgl-project/sglang/commit/ded9fcd09a43d5e7d5bb31a2bc3e9fc21bf65d2a

moe_align_block_size is based on:


https://github.com/sgl-project/sglang/commit/ba5112ff691d791a9e38c6c71f59324a5fcb49d0

Signed-off-by: Yang Chen <yangche@fb.com>
2025-02-03 13:09:50 +08:00
..
marlin_kernels
Update pre-commit hooks (#12475)
2025-01-27 17:23:08 -07:00
marlin_moe_ops.cu
[Bugfix] Fix support for dimension like integers and ScalarType (#9299)
2024-10-17 19:08:34 +00:00
moe_align_sum_kernels.cu
[Kernel] port sgl moe_align_block_size kernels (#12574)
2025-02-03 13:09:50 +08:00
moe_ops.h
[Kernel] port sgl moe_align_block_size kernels (#12574)
2025-02-03 13:09:50 +08:00
topk_softmax_kernels.cu
[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)
2024-06-09 16:23:30 -04:00
torch_bindings.cpp
[Kernel] port sgl moe_align_block_size kernels (#12574)
2025-02-03 13:09:50 +08:00
Powered by Gitea Version: 1.26.4 Page: 52ms Template: 1ms
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