 AlpinDale
|
7fffa507ff
build: build flash attention kernels inside aphrodite (#1085)
|
1 долоо хоног өмнө |
|
AlpinDale
|
9bdf8d5bfa
mamba: enable continuous batching for mamba kernels (#1055)
|
1 сар өмнө |
|
AlpinDale
|
239a8cae25
torch.compile: register all-reduce operations as custom ops (#1050)
|
1 сар өмнө |
|
AlpinDale
|
8976805f90
kernel: asymmetric AQ AZP quantization kernels (#1048)
|
1 сар өмнө |
|
AlpinDale
|
1390915778
multi-step: add support for flashinfer attention backend (#1033)
|
1 сар өмнө |
|
AlpinDale
|
a113309876
kernel: add meta functions for ops to prevent graph breaks (#1019)
|
1 сар өмнө |
|
AlpinDale
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
2 сар өмнө |
|
AlpinDale
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
2 сар өмнө |
|
AlpinDale
|
5b0eabe0e8
fix: compilation of gptq_marlin_gemm object (#800)
|
3 сар өмнө |
|
AlpinDale
|
f98e7b2f8c
feat: add HQQ quantization support (#795)
|
3 сар өмнө |
|
AlpinDale
|
0256ed236b
feat: windows support (#790)
|
3 сар өмнө |
 Naomiusearch
|
eee3cf5dab
fix: make AMD usable (#775)
|
3 сар өмнө |
|
AlpinDale
|
73177656ed
feat: quant_llm support (#755)
|
4 сар өмнө |
|
AlpinDale
|
a401f8e05d
feat: per-tensor token epilogue kernels (#630)
|
5 сар өмнө |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
5 сар өмнө |
