Satyam-53 8d4e05acef Remove CUDA to CPU and vice versa conversion ...

And more network payload logging

2026-09-07 18:49:49 -07:00

..

__init__.py

[Feat] add ray support (#838)

2025-10-16 23:17:54 -07:00

executor.py

Spark Diagg Inference/Serving commits

2026-09-07 18:49:49 -07:00

gpu_worker.py

[perf] Disable every offload path on unified memory, unblocking MiniMax H3 generation on one GB10 (#1715)

2026-08-26 15:32:56 -07:00

minimax_h3_disaggregated.py

Remove CUDA to CPU and vice versa conversion

2026-09-07 18:49:49 -07:00

multiproc_executor.py

[bugfix] Harden OpenAI serving after post-merge review (#1782)

2026-08-28 22:29:24 -07:00

ray_distributed_executor.py

[feat]: run FastH3 across two DGX Sparks with Ray sequence parallel (#1803)

2026-09-01 01:37:23 -07:00

ray_env.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00

ray_utils.py

[misc]: standardize install instructions on uv pip install (#1279)

2026-05-02 12:45:50 -07:00

worker_base.py

[feat] pre-commit support 120 col num (#1167)

2026-03-11 20:19:30 -07:00