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

..

backend

[SYCL] Initial cmake support of SYCL for AMD GPUs (#9658)

2024-10-02 13:57:18 +01:00

development

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

android.md

Update building for Android (#9672)

2024-10-07 09:37:31 -07:00

build.md

Arm AArch64: Documentation updates (#9321)

2024-09-09 10:02:45 +03:00

docker.md

Fix broken links in docker.md (#9306)

2024-09-04 13:45:28 +02:00

install.md

Reorganize documentation pages (#8325)

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