 AlpinDale
|
4d4e767838
ci: take one of fixing lint issues
|
пре 5 месеци |
 AlpinDale
|
0f4a9ee77b
quantized lm_head (#582)
|
пре 5 месеци |
|
AlpinDale
|
ae04f57ec1
feat: Pipeline Parallel support (#581)
|
пре 5 месеци |
|
AlpinDale
|
656459fd84
make fp8_e4m3 work on nvidia
|
пре 6 месеци |
|
AlpinDale
|
50b7c13db0
refactor: attention selector (#552)
|
пре 6 месеци |
|
AlpinDale
|
9fba7f1d36
remove quant_config from a few legacy models
|
пре 6 месеци |
|
AlpinDale
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
пре 6 месеци |
|
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
пре 7 месеци |
|
AlpinDale
|
9d81716bfd
[v0.5.3] Release Candidate (#388)
|
пре 9 месеци |
|
AlpinDale
|
f8dfac6372
chore: attention refactor and upstream sync apr01 (#365)
|
пре 10 месеци |
|
AlpinDale
|
da223153c6
feat&fix: cohere support and missing GPU blocks (#333)
|
пре 11 месеци |
|
AlpinDale
|
c41462cfcd
feat: exllamav2 quantization (#305)
|
пре 11 месеци |
|
AlpinDale
|
e31c6f0b45
feat: refactor modeling logic and support more models (#274)
|
пре 11 месеци |
