Robert ShawandWoosuk Kwon 56fe4c297c [TPU][Quantization] TPU W8A8 (#11785) ...

Co-authored-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-01-08 19:33:29 +00:00

..

__init__.py

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

2024-09-23 13:46:26 -04:00

fp8_utils.py

[Model] [Quantization] Support deepseek_v3 w8a8 fp8 block-wise quantization (#11523)

2024-12-26 15:33:30 -08:00

layer_utils.py

[Bugfix] Fix torch dynamo fixes caused by replace_parameters (#8748)

2024-09-24 14:33:21 -04:00

machete_utils.py

[Kernel] (2/N) Machete - Integrate into CompressedTensorsWNA16 and GPTQMarlin (#7701)

2024-09-23 13:46:26 -04:00

marlin_utils_fp8.py

[CI/Build] Avoid CUDA initialization (#8534)

2024-09-18 10:38:11 +00:00

marlin_utils_test_24.py

[Misc] Disambiguate quantized types via a new ScalarType (#6396)

2024-08-02 13:51:58 -07:00

marlin_utils_test_qqq.py

Support W4A8 quantization for vllm (#5218)

2024-07-31 07:55:21 -06:00

marlin_utils_test.py

[Misc] Fused MoE Marlin support for GPTQ (#8217)

2024-09-09 23:02:52 -04:00

marlin_utils.py

[Model][Quantization] HQQ support through Marlin kernel expansion (#9766)

2024-11-19 13:31:12 -08:00

quant_utils.py

[Kernel] Initial Machete W4A8 support + Refactors (#9855)

2024-11-18 12:59:29 -07:00

w8a8_utils.py

[TPU][Quantization] TPU W8A8 (#11785)

2025-01-08 19:33:29 +00:00