 AlpinDale
|
156f577f79
feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)
|
5 月之前 |
 AlpinDale
|
aba03b4756
feat: dynamic per-token activation quantization
|
5 月之前 |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
9 月之前 |
|
AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
10 月之前 |
|
AlpinDale
|
d9b65e6c5f
feat: DeepSeek MoE support (#237)
|
11 月之前 |
|
AlpinDale
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
1 年之前 |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
1 年之前 |
|
AlpinDale
|
7e72ce0a73
feat: mixtral tensor parallelism (#193)
|
1 年之前 |
|
AlpinDale
|
15a0454172
feat: FP8 KV Cache (#185)
|
1 年之前 |
|
AlpinDale
|
32844c1522
add GELU kernels and remove compile bloat
|
1 年之前 |
