SysML@Princeton
Popular repositories Loading
-
-
-
apparate
apparate PublicForked from dywsjtu/apparate
Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
Python
-
marconi
marconi PublicForked from ruipeterpan/marconi
Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
Python
-
specreason
specreason PublicForked from ruipeterpan/specreason
PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
Python
-
failfast
failfast PublicForked from ruipeterpan/failfast
Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]
Python
Repositories
- website Public
- specreason Public Forked from ruipeterpan/specreason
PoC for "SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning" [NeurIPS '25]
- failfast Public Forked from ruipeterpan/failfast
Artifact for "Fail Fast, Win Big: Rethinking the Drafting Strategy in Speculative Decoding via Diffusion LLMs" [arXiv '25]
- marconi Public Forked from ruipeterpan/marconi
Artifact for "Marconi: Prefix Caching for the Era of Hybrid LLMs" [MLSys '25 Outstanding Paper Award, Honorable Mention]
- apparate Public Forked from dywsjtu/apparate
Artifact for "Apparate: Rethinking Early Exits to Tame Latency-Throughput Tensions in ML Serving" [SOSP '24]
Top languages
Loading…
Most used topics
Loading…