 AlpinDale
|
46159b107a
formatting: pt1
|
vor 6 Monaten |
|
AlpinDale
|
bf2dd2bee9
feat: allow multiple sampling params in LLM class
|
vor 6 Monaten |
 AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
vor 8 Monaten |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
vor 9 Monaten |
|
AlpinDale
|
e42a78381a
feat: switch from pylint to ruff (#322)
|
vor 10 Monaten |
|
AlpinDale
|
ac82b67f75
feat: naive context shift and various QoL changes (#289)
|
vor 10 Monaten |
|
AlpinDale
|
c3a221eb02
feat: GGUF, QuIP#, and Marlin support (#228)
|
vor 11 Monaten |
|
AlpinDale
|
641bb0f6e9
feat: add custom allreduce kernels (#224)
|
vor 11 Monaten |
|
AlpinDale
|
c0aac15421
feat: S-LoRA support (#222)
|
vor 11 Monaten |
|
AlpinDale
|
8fa608aeb7
feat: replace Ray with NCCL for control plane comms (#221)
|
vor 11 Monaten |
|
AlpinDale
|
f013d714c0
chore: merge dev branch into main (#177)
|
vor 1 Jahr |
|
AlpinDale
|
2755a48d51
merge dev branch into main (#153)
|
vor 1 Jahr |
|
AlpinDale
|
8834ecf9de
chore: clean up refactor endpoints (#98)
|
vor 1 Jahr |
|
AlpinDale
|
c70abc7522
fix the LLM class for quantization
|
vor 1 Jahr |
|
AlpinDale
|
6b9561ef07
adapt TGI incremental detokenization
|
vor 1 Jahr |
|
AlpinDale
|
388d7545dd
fix: circular import
|
vor 1 Jahr |
|
AlpinDale
|
c761d38c69
fix: sort outputs and avoid unwanted list copy
|
vor 1 Jahr |
|
AlpinDale
|
56077f0f29
upstream: trust remote code
|
vor 1 Jahr |
|
AlpinDale
|
724852dc31
chore: refactoring cont.
|
vor 1 Jahr |
|
AlpinDale
|
5169163403
chore: add tokenizer mode for slow/fast tokenizers
|
vor 1 Jahr |
|
AlpinDale
|
07aa2a492f
upstream: add option to specify tokenizer
|
vor 1 Jahr |
|
AlpinDale
|
20a8235114
upstream: add
|
vor 1 Jahr |
|
AlpinDale
|
e52de7de70
feat: add API endpoint with FastAPI
|
vor 1 Jahr |
