Commit Graph
19 Commits
Author SHA1 Message Date
Zheng Wengang 1e6d041f78 [BugFix][VLM] keep Qwen3-VL MoE inference deepstack order (#34690) 2026-08-28 17:02:16 +08:00
Zheng Wengang 4ba7d5ad93 [BugFix][EPD] Early-release mooncake GPU embeddings; fix gpu_id via scheduler.ps (#31591) 2026-07-30 17:36:55 +08:00
Zheng Wengang 3d3ba4f746 [BugFix][EPD] Fix Mooncake source-MR lifecycle for multi-TP /send (#32071) 2026-07-27 15:06:01 +08:00
Zheng Wengang be7c13af07 [BugFix] Fix DS/Kimi crash on non-first PP ranks when resolving input length (#31752) 2026-07-24 12:19:02 -07:00
Zheng Wengangandsiyu 364b5f23e6 [BugFix][EPD] Harden zmq_to_scheduler receiver failures; sync error info across TP (#31592)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
2026-07-24 16:37:52 +08:00
Zheng Wengangandsiyu 6f55de0468 [EPD] Make encoder register/unregister health-check robust (#31576)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
2026-07-21 22:36:11 +08:00
Zheng Wengang 8b9fb13c4a [BugFix][EPD] adapt for qwen3.5-mtp & del duplicated logs (#24144) 2026-05-23 15:32:57 +08:00
Zheng Wengang 74c6294ba9 [BugFix][EPD]Fix Qwen3VLMoe encoder-only AttributeError (#25759) 2026-05-21 11:07:21 +08:00
Zheng Wengang ae0c036c24 [BugFix][EPD] fix embedding req_id transfer error (#23481) 2026-04-29 18:56:03 +08:00
Zheng Wengang 91825b8808 [FEAT][EPD] support encoder real health (#23343) 2026-04-27 13:21:28 +08:00
Zheng Wengangandsiyu 135af6dc92 [EPD][VLM] support video/audio input (#17824)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
2026-03-16 14:18:21 +08:00
Zheng Wengang da27d9bff6 [Bug-Fix][EPD]: skip log waiting-image-req for zmq_to_tokenzer/mooncake (#19555) 2026-03-06 14:39:22 +08:00
Zheng Wengang 0de0d74195 [EPD][Feat]support adaptive forward (#18118) 2026-03-05 21:12:30 +08:00
Zheng Wengang 68e31a3485 [BugFix][PD]Fix metadata_buffer_index leak when aborted in PD (#17483) 2026-02-09 11:34:29 +08:00
Zheng Wengangandsiyu a4df95c15f [EPD][Perf] parallelize ZMQ send for encode server (#16487)
Co-authored-by: siyu <liusy58@linux.alibaba.com>
2026-01-31 14:30:11 +08:00
Zheng Wengang cd3289c7a4 [BugFix][VLM] Correct weight loading with tie_word_embeddings == False (#15398) 2025-12-26 17:30:50 -08:00
Zheng Wengang fde2decf8b [BugFix][Qwen3-VL]: add metadata for video in qwen3-vl (#11377) 2025-10-21 15:36:01 -07:00
Zheng Wengang b2c8566920 [BugFix][Qwen3-VL]: fix cu_seqlens in qwen3-vl (#11458) 2025-10-14 22:16:49 -07:00
2d120f8b18 [Feature][Multimodal] Implement LRU cache for multimodal embeddings (#8292)
Signed-off-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
2025-08-06 23:21:40 -07:00