Logo
Explore Help
Register Sign In
biondizzle/vllm
1
0
Fork 0
You've already forked vllm
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity
Files
18c2e30c5754dc83f86d9b8c75af0499a77e4b3f
vllm/csrc/moe
History
ElizaWszola d081da0064 [Bugfix] Fix Marlin MoE act order when is_k_full == False (#8741)
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2024-09-28 18:19:40 -07:00
..
marlin_kernels
[Kernel] Split Marlin MoE kernels into multiple files (#8661)
2024-09-24 09:31:42 -07:00
marlin_moe_ops.cu
[Bugfix] Fix Marlin MoE act order when is_k_full == False (#8741)
2024-09-28 18:19:40 -07:00
marlin_moe_ops.h
[Kernel] Enable 8-bit weights in Fused Marlin MoE (#8032)
2024-09-16 09:47:19 -06:00
moe_ops.h
[Kernel][Misc] Use TORCH_LIBRARY instead of PYBIND11_MODULE for custom ops (#5047)
2024-06-09 16:23:30 -04:00
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] Enable 8-bit weights in Fused Marlin MoE (#8032)
2024-09-16 09:47:19 -06:00
Powered by Gitea Version: 1.25.2 Page: 67ms Template: 2ms
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