Logo
Explore Help
Register Sign In
wassname/vllm
Watch 1
Star 0
Fork 0
mirror of https://github.com/wassname/vllm.git synced 2026-07-29 11:29:22 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
1fe0a4264aa94ceeccc7e8d99ac0d72f0560f541
vllm/csrc/moe
T
History
ElizaWszolaGitHubTyler Michael Smith
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: 1.27.1 Page: 38ms Template: 2ms
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