 AlpinDale
|
c2be1b9f29
formatting
|
hace 5 meses |
|
AlpinDale
|
cbfc7f96d6
potential fix
|
hace 5 meses |
|
AlpinDale
|
7d3194e7f4
revert #244
|
hace 5 meses |
 AlpinDale
|
3ab36e6b2d
feat: extended RoPE for Llama 3.1 (#543)
|
hace 5 meses |
|
AlpinDale
|
c9d6f9f164
fix formatting
|
hace 5 meses |
|
AlpinDale
|
0e75803a50
why was this ignored by git?
|
hace 5 meses |
|
AlpinDale
|
0d3562a7f9
MQA in triton FA
|
hace 5 meses |
|
AlpinDale
|
8de8034f8b
include fp8 compilation in rocm
|
hace 5 meses |
|
AlpinDale
|
0f7ef9ef7c
fix: import in selector
|
hace 5 meses |
|
AlpinDale
|
36660b55c2
chore: mixtral fp8 w/ static scales (#542)
|
hace 5 meses |
|
AlpinDale
|
c21af7acad
feat: `DistributedGPUExecutor` abstract class (#541)
|
hace 5 meses |
|
AlpinDale
|
b178ae4b4a
chore: generalize linear_method to be quant_method (#540)
|
hace 5 meses |
|
AlpinDale
|
a6a627d745
fix aqlm compilation
|
hace 5 meses |
|
AlpinDale
|
aed64884c6
feat: prompt logprobs with chunked prefill (#539)
|
hace 5 meses |
 Naomiusearch
|
9bcbf61296
There's no aphrodite.py in outlines repo (#531)
|
hace 6 meses |
 cloud11665
|
cc9a801eed
[bugfix] change c++ std to 20 (#529)
|
hace 6 meses |
|
AlpinDale
|
ed759f065d
chore: tokenizer_revision -> revision
|
hace 6 meses |
|
AlpinDale
|
2e0b115ce1
move func tracing to utils
|
hace 6 meses |
|
AlpinDale
|
41338053e7
feat: add shutdown method to engine
|
hace 6 meses |
|
AlpinDale
|
199e776722
chore: move ray utils to executor dir
|
hace 6 meses |
|
AlpinDale
|
e7b1368156
feat: Phi3 support
|
hace 6 meses |
|
AlpinDale
|
1225c4dfd6
fix: illegal mem access crash for marlin
|
hace 6 meses |
|
AlpinDale
|
d1a3c7bc2c
chore: simplify try-finally logic in pynccl
|
hace 6 meses |
|
AlpinDale
|
440384d776
chore: use nvidia-ml-py instead of pynvml
|
hace 6 meses |
|
AlpinDale
|
46159b107a
formatting: pt1
|
hace 6 meses |
|
AlpinDale
|
4c746d8baa
chore: init nccl using the gloo backend
|
hace 6 meses |
|
AlpinDale
|
bf2dd2bee9
feat: allow multiple sampling params in LLM class
|
hace 6 meses |
 Orion
|
a2a24e9b0d
feat: list support in message.content (#503)
|
hace 6 meses |
 Bruno Renié
|
9c45fe9a2a
openai: fix metrics endpoint (#512)
|
hace 6 meses |
|
AlpinDale
|
fca911ee0a
vLLM Upstream Sync (#526)
|
hace 6 meses |
