Commit Graph

15 Commits

Author SHA1 Message Date
Sunny-bot1
8224b21525 Refactor moe_topk_select op to use apply_norm_weight as a template parameter (#3345)
* Refactor moe_topk_select op to use apply_norm_weight as a template parameter

* update test
2025-08-13 08:44:16 +08:00
yangjianfengo1
89397516a8 [New Feature] Support W4Afp8 MoE GroupGemm (#3171)
* init

* 增加多线程编译

* fix bug

* fix bug

* code style

* 增加fp16

* 将print替换成assert

* 修复stmatrix

* 减小单测shape

* 减小单测shape
2025-08-06 10:34:05 +08:00
Yuan Xiaolan
af543b7f0f revise get_moe_scores (#3164) 2025-08-05 16:43:07 +08:00
chen
04fc7eb931 fix test_air_top_p_sampling name (#3211) 2025-08-05 15:47:50 +08:00
ming1753
14ed75f7d3 [Test] scaled_gemm_f8_i4_f16 skip test while sm != 89 (#3210) 2025-08-05 15:25:28 +08:00
yangjianfengo1
40f7f3e0d8 [New Feature] fa3 支持flash mask (#3184)
* 支持flash mask

* 修改test_flash_mask

* 修改test.sh
2025-08-05 12:20:48 +08:00
JYChen
c34088b0fd fix stop seq unittest (#3126) 2025-08-01 16:50:05 +08:00
AIbin
28fff1b035 Revert "Add uinttest for moe_ffn_wint2. (#3037)" (#3085)
This reverts commit 327e1943fa.
2025-07-30 19:04:07 +08:00
YuanRisheng
eeadbf332a delete unused unittest (#3065) 2025-07-30 15:11:58 +08:00
Yiqun Liu
327e1943fa Add uinttest for moe_ffn_wint2. (#3037)
Change-Id: Ifd452527eaf87ea96c3fa4fa9aeb17729b33c2de
2025-07-30 15:03:09 +08:00
JYChen
dafe02a7b9 [stop sequence] support stop sequence (#3025)
* stop seqs in multi-ends

* unittest for gpu stop op

* kernel tid==0
2025-07-29 14:17:37 +08:00
Zero Rains
25698d56d1 polish code with new pre-commit rule (#2923) 2025-07-19 23:19:27 +08:00
ming1753
1f15ca21e4 [Feature] support prompt repetition_penalty (#2806)
Some checks failed
Deploy GitHub Pages / deploy (push) Has been cancelled
2025-07-17 12:05:52 +08:00
Jiang-Jia-Jun
92c2cfa2e7 Sync v2.0 version of code to github repo 2025-06-29 23:29:37 +00:00
jiangjiajun
684703fd72 [LLM] First commit the llm deployment code 2025-06-09 19:20:15 +08:00