22dimensions a8730e7a3c [Doc] update quantization docs with QwQ-32B-W8A8 example (#835) ...

1. replace deepseek-v2-lite model with more pratical model QwQ 32B
2. fix some incorrect commands
3. replase modelslim version with a more formal tag

Signed-off-by: 22dimensions <waitingwind@foxmail.com>

2025-05-17 15:25:17 +08:00

..

index.md

[Doc] Add deepsee-v2-lite w8a8 quantization turorial (#630)

2025-04-28 17:14:26 +08:00

multi_node.md

[CI] enable custom ops build (#466)

2025-04-12 10:24:53 +08:00

multi_npu_quantization.md

[Doc] update quantization docs with QwQ-32B-W8A8 example (#835)

2025-05-17 15:25:17 +08:00

multi_npu.md

[Doc]Fix tutorial doc expression (#319)

2025-03-13 15:24:05 +08:00

single_npu_multimodal.md

[Doc] Add the release note for 0.7.3rc1 (#285)

2025-03-13 17:57:06 +08:00

single_npu.md

Update installation and tutorial doc (#711)

2025-04-28 21:52:17 +08:00