DandinPower 73969b44b1 feat: use bitsqueeze as communication compression library to replace the previous quantization/k_quantization/sparsity. Also add a new argument call comm_compression_threshold to allow user can set a threshold for compression (good for only compress prefilling tokens)

2025-12-06 21:08:10 +08:00

..

llama-star

Reorganize documentation pages (#8325)

2024-07-05 18:08:32 +02:00

create_args_for_prima.md

feat: use bitsqueeze as communication compression library to replace the previous quantization/k_quantization/sparsity. Also add a new argument call comm_compression_threshold to allow user can set a threshold for compression (good for only compress prefilling tokens)

2025-12-06 21:08:10 +08:00

debugging-tests.md

Reorganize documentation pages (#8325)

2024-07-05 18:08:32 +02:00

HOWTO-add-model.md

docs: fix links in development docs [no ci] (#8481)

2024-07-15 14:46:39 +03:00

token_generation_performance_tips.md

docs: fix links in development docs [no ci] (#8481)

2024-07-15 14:46:39 +03:00