Yilong Zhao
|
f30d1d0b0a
|
logits: remove blocking H2D copy (#24627)
|
2026-05-08 13:22:13 -07:00 |
|
Yilong Zhao
|
f67292539f
|
spec: gate dp mlp sync with server args (#24177)
|
2026-04-30 16:29:41 -07:00 |
|
Yilong Zhao
|
b1efce342c
|
env: add knob to control SWA eviction interval (#22645)
|
2026-04-13 15:37:59 -07:00 |
|
Yilong Zhao
|
58f863956c
|
cuda graph: adjust capture time num-non-padded-tokens to align capture with replay (#22404)
|
2026-04-11 10:27:50 +08:00 |
|
Yilong Zhao
|
fe92f3563c
|
dp: add profile req hook (#22083)
|
2026-04-03 20:47:09 -07:00 |
|
Yilong Zhao
|
f30df723bf
|
scheduler: add prefill-only update in merge batch (#21840)
|
2026-04-01 23:33:06 -07:00 |
|
Yilong Zhao
|
1f7cee81da
|
[moe] add customized option to moe-a2a-backend (#21786)
|
2026-03-31 16:32:47 -07:00 |
|
Yilong Zhao
|
343998865a
|
perf: pad max-num-requests in decode cuda graph for higher coverage (#20978)
|
2026-03-22 17:06:16 -07:00 |
|
Yilong Zhao
|
26f709e97d
|
misc: make prefill-delayer compatible with multiple types of mem pool (#20979)
|
2026-03-20 00:05:53 -07:00 |
|
Yilong Zhao
|
95327458ee
|
misc: add BatchTokenizerReq hook into dp controller (#20981)
|
2026-03-19 23:59:53 -07:00 |
|
Yilong Zhao
|
6ffc74efd7
|
[Metrics] Add overlap bubble timing, full KV usage gauge, and prefill cuda graph tracking (#19982)
|
2026-03-06 17:41:27 -08:00 |
|
Yilong Zhao
|
1bbfed0539
|
[misc] add env for http keep alive timeout (#19847)
|
2026-03-04 22:00:51 -08:00 |
|
Yilong Zhao
|
79b1d2bac6
|
[loader] support presharded fused mlp loading (#19519)
|
2026-02-27 20:37:24 -08:00 |
|
Yilong Zhao
|
07da4bed7b
|
[cache] add conservative estimation (#19482)
|
2026-02-27 18:14:46 +08:00 |
|
Yilong Zhao
|
de3d1e7669
|
[misc] use ORJSONResponse in http-server generate (#19191)
|
2026-02-25 21:26:25 -08:00 |
|
Yilong Zhao
|
d5307ce022
|
[misc] adding metadata field in UpdateWeightFromDiskReqInput (#18821)
|
2026-02-17 12:14:15 +08:00 |
|