Logo
Explore Help
Register Sign In
EngineX-Hygon/sglang
5
0
Fork 0
You've already forked sglang
Code Issues Pull Requests Actions 7 Projects Releases Wiki Activity
Files
6cdcbcc674542e58a441de4e40533bea522180c6
sglang/benchmark/kernels
History
Yuan Luo 968e181826 Fix triton_fused_moe unit test and benchmark (#9276)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-08-18 00:54:33 -07:00
..
all_reduce
support 1 shot allreduce in 1-node and 2-node using mscclpp (#6277)
2025-06-04 22:11:24 -07:00
decoding_attention_triton
[CI] Remove unused imports with Ruff to pre-commit config, only to benchmarks/docs/examples folder (#3969)
2025-03-27 19:45:02 -07:00
deepep
Support tuning DeepEP configs (#6742)
2025-05-29 08:12:22 -07:00
deepseek
refactor apply_w8a8_block_fp8_linear in fp (#6545)
2025-05-29 00:15:11 -07:00
fused_moe_triton
Fix triton_fused_moe unit test and benchmark (#9276)
2025-08-18 00:54:33 -07:00
minmax-text-01-lightning_attention
[CI] Remove unused imports with Ruff to pre-commit config, only to benchmarks/docs/examples folder (#3969)
2025-03-27 19:45:02 -07:00
quantization
Replace time.time() to time.perf_counter() for benchmarking. (#6178)
2025-05-11 14:32:49 -07:00
rmsnorm
[CI] Remove unused imports with Ruff to pre-commit config, only to benchmarks/docs/examples folder (#3969)
2025-03-27 19:45:02 -07:00
scheduler_batch
[test] add ut and bm for get_last_loc (#6746)
2025-05-29 11:47:21 -07:00
sliding_window_attention_triton
Optimize triton swa kernel by skipping computation (#8860)
2025-08-06 21:37:50 +08:00
Powered by Gitea Version: 1.24.3 Page: 115ms Template: 7ms
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API