 AlpinDale
|
fa84f8102e
kernels: split marlin kernels for faster compile, fix MoE, temporarily remove HQQ (#1119)
|
5 päivää sitten |
|
AlpinDale
|
949f974c59
(1/N) XQA: integrate the XQA CUDA kernels within Aphrodite (#1115)
|
1 viikko sitten |
 AlpinDale
|
98e174b1f4
build: fix cutlass fetch warning
|
2 viikkoa sitten |
|
AlpinDale
|
7fffa507ff
build: build flash attention kernels inside aphrodite (#1085)
|
2 viikkoa sitten |
|
AlpinDale
|
4a7cb8f232
rocm: add custom paged attention kernels for ROCm (#1043)
|
1 kuukausi sitten |
|
AlpinDale
|
51d24fc7c0
build: shallow clone cutlass 3.5.1 tag (#1010)
|
1 kuukausi sitten |
|
AlpinDale
|
313e198557
api: implement OpenAI-compatible tools API for Hermes/Mistral models (#993)
|
1 kuukausi sitten |
|
AlpinDale
|
9f3e7c86e2
feat: add fused Marlin MoE kernel (#934)
|
1 kuukausi sitten |
|
AlpinDale
|
2a60b8f8c9
kernel: do not compile machete for cuda 11 and below (#901)
|
1 kuukausi sitten |
|
AlpinDale
|
afadef06cd
build: pass `PYTHONPATH` from setup.py to cmake (#879)
|
2 kuukautta sitten |
 Naomiusearch
|
4f9fea4c4d
fix: ROCm build (#817)
|
2 kuukautta sitten |
|
AlpinDale
|
93bc863591
feat: Machete Kernels for Hopper GPUs (#842)
|
2 kuukautta sitten |
|
AlpinDale
|
bfc8988116
feat: add cuda sampling kernels for top_k and top_p (#828)
|
2 kuukautta sitten |
|
AlpinDale
|
0256ed236b
feat: windows support (#790)
|
3 kuukautta sitten |
|
Naomiusearch
|
eee3cf5dab
fix: make AMD usable (#775)
|
3 kuukautta sitten |
|
AlpinDale
|
73177656ed
feat: quant_llm support (#755)
|
4 kuukautta sitten |
|
AlpinDale
|
ec32f999bc
build: bump cmake to 3.26 (#691)
|
5 kuukautta sitten |
|
AlpinDale
|
f1d0b77c92
[0.6.0] Release Candidate (#481)
|
5 kuukautta sitten |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
9 kuukautta sitten |
|
AlpinDale
|
e120404436
Revert "feat: CMake Build System Generator (#332)"
|
11 kuukautta sitten |
|
AlpinDale
|
ad6802690f
feat: CMake Build System Generator (#332)
|
11 kuukautta sitten |
