- 19 Nov, 2025 6 commits
-
-
niuhb authored
# Conflicts: # python/sglang/srt/layers/attention/dcu_mla_backend.py # python/sglang/srt/layers/attention/flashattention_backend.py # python/sglang/srt/model_executor/forward_batch_info.py # sgl-kernel/csrc/common_extension_rocm.cc # sgl-kernel/include/sgl_kernel_ops.h
-
lizhigong authored
支持w8a8 compile,注册自定义算子解决部分断图问题 See merge request OpenDAS/sglang!31
-
renzhc authored
-
shangxl authored
增加dcu_assign_req_to_token_pool、dcu_get_last_loc、dcu_assign_extend_cache_locs、dcu_create_flashmla_kv_indices、dcu_create_chunked_prefix_cache_kv_indices算子
-
maxiao1 authored
修复w8a8_marlin tp pp See merge request OpenDAS/sglang!30
-
maxiao1 authored
-
- 18 Nov, 2025 5 commits
- 17 Nov, 2025 2 commits
- 15 Nov, 2025 2 commits
- 14 Nov, 2025 6 commits
- 13 Nov, 2025 3 commits
- 12 Nov, 2025 5 commits
- 11 Nov, 2025 6 commits
- 10 Nov, 2025 5 commits