Alexander Borzunov
|
8c546d988a
Test Llama, rebalancing, throughput eval, and all CLI scripts (#452)
|
1 年之前 |
Alexander Borzunov
|
1a78638c02
Test that bitsandbytes is not imported when it's not used (#351)
|
1 年之前 |
Alexander Borzunov
|
cb3f018f9f
Add LLaMA support (#323)
|
1 年之前 |
Alexander Borzunov
|
6137b1b4b0
Replace .make_sequence(..., mode="random") with mode="max_throughput" (#313)
|
1 年之前 |
Alexander Borzunov
|
8f6342a861
Refactor RemoteSequenceManager (#309)
|
1 年之前 |
Alexander Borzunov
|
21c3526ec1
Start SequenceManager's thread only after first .make_sequence() (#301)
|
1 年之前 |
Max Ryabinin
|
793726b041
Speed up loading blocks using init with meta weights (#285)
|
1 年之前 |
Alexander Borzunov
|
fee19e9b9b
Use get_logger(__name__) instead of get_logger(__file__) (#265)
|
1 年之前 |
justheuristic
|
012f840f7e
Use length-weighted sampling in routing for inference (#204)
|
1 年之前 |
Alexander Borzunov
|
668b736031
Fix logging: do not duplicate lines, enable colors in Colab (#156)
|
1 年之前 |
justheuristic
|
8dc0f513ba
Hotfix span selection (#110)
|
1 年之前 |
justheuristic
|
a2066a4096
Optimize RemoteSequenceManager (#106)
|
1 年之前 |