|
2286e85e77
|
pass a_scale from fp8 quant result instead of hard code to 1.0f (#10241)
Co-authored-by: Yichen Wang <yichen.wang@bytedance.com>
Co-authored-by: Jinwu Guo <641876696@qq.com>
|
2025-09-10 12:56:05 -07:00 |
|
|
Rain Jiang
|
df5407fb53
|
Revert "feat: add fused moe config for Qwen3-30B-A3B on B200" (#10185)
|
2025-09-08 18:11:15 -07:00 |
|
|
Rain Jiang
|
7a40e4f4a6
|
fix the cutlass moe tests (#10182)
|
2025-09-08 16:24:55 -07:00 |
|
|
Rain Jiang
|
6049ca209e
|
move compile threads to an option to avoid OOM on low memory host (#10123)
|
2025-09-07 21:36:14 -07:00 |
|
|
Rain Jiang
|
7802586cab
|
fix the fp8 topk_config.correction_bias is none bug (#10040)
|
2025-09-07 20:28:14 -07:00 |
|
|
Rain Jiangandgemini-code-assist[bot]
|
9db8025376
|
support fp8 kvcache for hybrid attn backend on GPT-OSS (#9783)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-09-01 19:17:12 +00:00 |
|
|
Rain Jiang
|
6b39f9cf8c
|
Support compile sgl-kernel on cuda 13.0 (#9721)
|
2025-08-28 10:18:03 -07:00 |
|
|
Rain Jiang
|
79e6a8a6ac
|
support cuda 13.0 and trtllm kernel by Aug 25 2025 (#9495)
|
2025-08-26 23:13:27 -07:00 |
|