13 Commits
Author SHA1 Message Date
silencejade 575759d90a [NPU] Support nccl backend for --remote-instance-weight-loader (#39413) 2026-09-17 17:28:15 +08:00
silencejade 78eef34356 [NPU] [BugFix] Fix discontinuous input for FIA operator in GLM4.7‑Flash (#36170) 2026-08-29 00:03:05 -07:00
silencejade b03ac355e7 [NPU] [FIX] Fix non-contiguous parameter issue in FIA operator (#34936) 2026-08-20 20:43:40 +08:00
silencejade 593777c046 [FIX] [benchmark] Fix flush_cache failure after warmup by waiting for server idle (#33527) 2026-08-05 21:27:43 +08:00
silencejade 72e415dfc8 [Bugfix] Fix prefill suspension caused by delayed negotiate_should_allow_prefill invocation (#32389) 2026-07-26 14:59:26 +08:00
silencejade 09071be105 [NPU] [FIX] Fix performance degradation of Qwen3.5-397B-A17B (#32130) 2026-07-23 14:05:10 +08:00
silencejade ff51acd67b [NPU] Qwen3-VL-8B use split_qkv_rmsnorm_rope for extend (#29627) 2026-06-30 15:55:50 +08:00
silencejade f85cc94d82 [NPU] Qwen3-VL-30B use split_qkv_rmsnorm_rope for extend (#29505) 2026-06-29 14:35:19 +08:00
silencejade 6c6fa19a90 [NPU] Support fsdp for rl_on_policy_target (#29128) 2026-06-24 14:57:19 +08:00
silencejade 23a825c694 [DOC] [NPU] add qwen3.5-397b best practice to doc_new (#26709) 2026-05-30 14:20:24 +08:00
silencejade e603beab55 [NPU] Add Qwen3.5-397B-A17B best practice doc (#25594) 2026-05-21 10:02:12 +08:00
silencejade 407665a7d4 [NPU] Fix mrope_position computation in Eagle Worker v2 with PlanStream (#23423) 2026-05-11 09:43:37 +08:00
silencejade 0fc9598b3e [NPU] Support radix-cache with mamba-extra-buffer for Qwen3.5 (#23891) 2026-05-11 09:40:44 +08:00