 AlpinDale
|
58e89e29d9
add custom bias to attention.py
|
il y a 9 mois |
 AlpinDale
|
9810daa699
feat: INT8 KV Cache (#298)
|
il y a 10 mois |
|
AlpinDale
|
31c95011a6
feat: FP8 E5M2 KV Cache (#226)
|
il y a 11 mois |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
il y a 11 mois |
|
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
il y a 1 an |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
il y a 1 an |
 50h100a
|
fa0ae5a2c9
feat: new mirostatv2 implementation (#96)
|
il y a 1 an |
|
AlpinDale
|
69204736de
Revert "fix: sync CPU delay in sampler (#93)"
|
il y a 1 an |
|
AlpinDale
|
ce66e1df56
fix: sync CPU delay in sampler (#93)
|
il y a 1 an |
|
AlpinDale
|
efc6f7fbec
chore: reformats (#90)
|
il y a 1 an |
|
AlpinDale
|
3d72f05c7b
feat: flattened 1D tensor -> 2D tensor (#85)
|
il y a 1 an |
|
AlpinDale
|
e6be0118c9
feat: prompt logprobs and batched samplers (#77)
|
il y a 1 an |
|
AlpinDale
|
3bf6197afb
fix: prompt processing delay introduced by #66 (#71)
|
il y a 1 an |
|
AlpinDale
|
cbeeabeb9a
feat: mistral support (#20)
|
il y a 1 an |
|
AlpinDale
|
34295abec4
chore: use xformers attention bias and add docs
|
il y a 1 an |
|
AlpinDale
|
5e82533d02
upstream: add option to specify tokenizer
|
il y a 1 an |
|
AlpinDale
|
cf9dc9b6cd
feat: write model metadata
|
il y a 1 an |
