- 05 Jan, 2026 1 commit
-
-
wanglong3 authored
-
- 04 Jan, 2026 1 commit
-
-
wujl5 authored
-
- 22 Dec, 2025 1 commit
-
-
王敏 authored
[feat]1.优化ep sequence parallel,区分主模型和mtp逻辑;2.ep sequence parallel添加cudagraph padding到tp_size;3.修复共享专家和deepep combine overlap
-
- 18 Dec, 2025 1 commit
-
-
王敏 authored
-
- 17 Dec, 2025 1 commit
-
-
zhuwenwen authored
-
- 16 Dec, 2025 1 commit
-
-
zhuwenwen authored
-
- 04 Dec, 2025 1 commit
-
-
zhuwenwen authored
add VLLM_USE_LIGHTOP_RMS_ROPE_CONCAT when use USE_FUSED_RMS_QUANT and USE_FUSED_CUSTOM_ALL_REDUCE_RMS_QUANT
-
- 02 Dec, 2025 1 commit
-
-
zhuwenwen authored
-
- 01 Dec, 2025 1 commit
-
-
zhuwenwen authored
-
- 26 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 20 Nov, 2025 2 commits
- 18 Nov, 2025 1 commit
-
-
wujl5 authored
-
- 04 Nov, 2025 1 commit
-
-
zhuwenwen authored
-
- 24 Oct, 2025 1 commit
-
-
zhuwenwen authored
add VLLM_USE_LIGHTOP_MOE_SUM_MUL_ADD
-
- 15 Oct, 2025 1 commit
-
-
yangql authored
-
- 13 Oct, 2025 2 commits
- 25 Sep, 2025 1 commit
-
-
zhuwenwen authored
[kernels] update moe_align_block_size and moe_sum interface
-
- 24 Sep, 2025 1 commit
-
-
zhuwenwen authored
[FIX] 修复mtp和VLLM_USE_TRITON_CAT不能一起开的bug
-
- 22 Sep, 2025 1 commit
-
-
wujl5 authored
-
- 14 Sep, 2025 1 commit
-
-
wujl5 authored
-
- 01 Sep, 2025 2 commits
- 29 Aug, 2025 1 commit
-
-
yangql authored
-
- 25 Jul, 2025 1 commit
-
-
yangql authored
-
- 15 Jul, 2025 1 commit
-
-
zhuwenwen authored
-
- 30 Jun, 2025 2 commits
-
-
gaoqiong authored
-
Chendi.Xue authored
Signed-off-by:Chendi Xue <chendi.xue@intel.com>
-
- 26 Jun, 2025 1 commit
-
-
Bowen Wang authored
Signed-off-by:Bowen Wang <abmfy@icloud.com>
-
- 13 Jun, 2025 1 commit
-
-
gaoqiong authored
-
- 05 Jun, 2025 2 commits
- 03 Jun, 2025 1 commit
-
-
Simon Mo authored
Signed-off-by:simon-mo <simon.mo@hey.com>
-
- 27 May, 2025 2 commits
- 23 May, 2025 1 commit
-
-
lizhigong authored
-
- 22 May, 2025 2 commits
- 15 May, 2025 1 commit
-
-
Harry Mellor authored
Signed-off-by:Harry Mellor <19981378+hmellor@users.noreply.github.com>
-