Robert Shaw 082ecd80d5 [ Bugfix ] Fix AutoFP8 fp8 marlin (#6609)

2024-07-20 17:25:56 -06:00

..

compressed_tensors

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

utils

[ Bugfix ] Fix AutoFP8 fp8 marlin (#6609)

2024-07-20 17:25:56 -06:00

__init__.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

aqlm.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

awq.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

base_config.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

bitsandbytes.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

deepspeedfp.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

fbgemm_fp8.py

[ Kernel ] Enable fp8-marlin for fbgemm-fp8 models (#6606)

2024-07-20 18:50:10 +00:00

fp8.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

gptq_marlin_24.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

gptq_marlin.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

gptq.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

marlin.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00

schema.py

Enable scaled FP8 (e4m3fn) KV cache on ROCm (AMD GPU) (#3290)

2024-04-03 14:15:55 -07:00

squeezellm.py

[ Misc ] fbgemm checkpoints (#6559)

2024-07-20 09:36:57 -07:00