 AlpinDale
|
50c2434267
move megatron to a top-level directory
|
пре 9 месеци |
 sgsdxzy
|
638547ec98
fix: Improve cohere model. (#404)
|
пре 9 месеци |
 AlpinDale
|
fa083286e3
Speculative Decoding Part 4: Lookahead scheduling (#402)
|
пре 9 месеци |
|
sgsdxzy
|
47370d2ad5
Fix cohere for command-r+ (#394)
|
пре 9 месеци |
|
AlpinDale
|
0f1399c135
feat: attention refactor part 2
|
пре 9 месеци |
|
AlpinDale
|
d1786645a3
fix formatting
|
пре 9 месеци |
|
AlpinDale
|
ace9bcd53f
fix gptq for cohere
|
пре 9 месеци |
|
AlpinDale
|
688d56993a
add logit scale for command-r
|
пре 9 месеци |
|
AlpinDale
|
06d88bb8fd
logitproc for cohere
|
пре 9 месеци |
|
AlpinDale
|
582e9efc12
support command-r+ model
|
пре 9 месеци |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
пре 9 месеци |
|
AlpinDale
|
da223153c6
feat&fix: cohere support and missing GPU blocks (#333)
|
пре 10 месеци |
