This website requires JavaScript.
Explore
Help
Register
Sign In
minke.yu
/
sglang
Watch
1
Star
0
Fork
0
Code
Issues
Pull Requests
Actions
12
Packages
Projects
Releases
Wiki
Activity
Files
786cdfc040be49f2b0dfbe59ca40745abd48cff2
sglang
/
test
/
registered
/
unit
/
model_executor
/
runner
T
History
Liangsheng Yin
d61f618276
[Perf] spec: Let DSPARK prefill publish read-done by placing its draft KV inject before the target forward (
#45682
)
2026-10-21 18:40:44 -07:00
..
test_decode_cuda_graph_runner.py
[AMD] Resolving bug in per batch size graph capture due to multiple capture runs per batch size (
#39840
)
2026-10-10 00:47:13 -07:00
test_decode_cuda_graph_shared_read_fence.py
[AMD] [GLM-5.3-Flash] Enable FP8 and MXFP4 serving on gfx950 (
#39273
)
2026-10-01 15:59:44 -07:00
test_flashinfer_autotune_sync.py
[Feat] runtime: Include FlashInfer’s default tactic in startup tuning. (
#43927
)
2026-10-15 15:30:45 +08:00
test_graph_routing_context.py
[Refactor] moe: Derive routing inputs from the layer and active forward (
#44994
)
2026-10-20 16:26:15 -07:00
test_hidden_state_graph_recapture.py
[DSv4.1] Support TRT-LLM decoder bounded replay with BCG (
#44326
)
2026-10-14 17:39:52 -07:00
test_prefill_cuda_graph_padding.py
[Perf] prefill-cuda-graph: Make prefill shared-read completion explicit and default-on (
#37958
)
2026-10-20 16:12:55 -07:00
test_prefill_shared_read_done.py
[Perf] spec: Let DSPARK prefill publish read-done by placing its draft KV inject before the target forward (
#45682
)
2026-10-21 18:40:44 -07:00