16 Commits
Author SHA1 Message Date
Vladislav NosivskoyandXinyuan Tong 154f0ac662 Fix DSpark and DP/EP (#33098)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2026-08-04 00:35:57 -07:00
Vladislav Nosivskoy 2ad9a5b576 [UnifiedTree] Use dense model for HiCache+CP KL tests (#28726) 2026-06-20 00:18:01 +08:00
Vladislav NosivskoyandZhangheng b7ae7149e8 [HiCache] Fix SWA L3 cache miss due to a prefetch/hit len mismatch (#27291)
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-06-18 14:55:00 +08:00
Vladislav NosivskoyandZhiqiang Xie bcf298c28c [HiCache & Bench] add cache hit breakdown in bench_serving (#22053)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
2026-06-17 16:02:30 -07:00
Vladislav Nosivskoy 62c505a196 [HiCache][Dsv4] Don't cache C128 State pool in L3 (#27293) 2026-06-08 21:23:26 +08:00
Vladislav NosivskoyandZhangheng 63dc20ae6c [UnifiedTree] Add CP sync (#25395)
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-06-03 16:10:27 +08:00
Vladislav Nosivskoy 34ea682a07 [UnifiedTree] gate load back pre-evict on full-attn availability only (#26302)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-05-29 00:30:03 +08:00
Vladislav Nosivskoy 60a1dacd89 [HiCache] return cached_tokens_details in sglext for streaming responses (#22055)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-05-04 12:30:17 -07:00
Vladislav Nosivskoy 28ee08c172 [HiCache] Add synchronization for context parallelism (#20460)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-04-28 02:13:07 +08:00
Vladislav Nosivskoy 4028a73c10 [KV-Events] Fix kv events events publishing for CP (#22983)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-04-20 17:34:38 +08:00
Vladislav Nosivskoyandhzh0425 79c82c5c42 [HiCache] Fix write_backup return type when parent not backed up (#22185)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
2026-04-08 16:42:57 +08:00
Vladislav NosivskoyandLianmin Zheng c37200f5e4 Scope streaming backlog coalescing to incremental_streaming_output mode (#21037)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
2026-03-27 17:29:54 -07:00
Vladislav Nosivskoyandishandhanani b9dba851a0 Fix streaming token ids data loss under load (#19977)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2026-03-18 12:23:45 -07:00
Vladislav Nosivskoy afd91e8782 [DSv32] Fix MTP and CP compatability (#19062)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2026-02-21 11:10:34 +08:00
Vladislav Nosivskoyandishandhanani e166ca8758 [HiCache] feat: Add detailed cache hit breakdown for HiCache in sglext and Prometheus metrics (#17648)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2026-02-03 11:45:35 -08:00
Vladislav Nosivskoyandishandhanani d70c265533 SGLang Tracing: fix attribute errors (header extraction & bootstrap span closing) (#15693)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
Co-authored-by: ishandhanani <82981111+ishandhanani@users.noreply.github.com>
2025-12-27 22:44:31 -06:00