Commit Graph
11792 Commits
Author SHA1 Message Date
Alex Nails 332ec5e5ee [release] install rust toolchain in main dockerfile (#23014) 2026-04-20 09:50:08 -07:00
Makcum888eandronnie_zheng 39c720d1b9 [Diffusion][NPU][CI] update perf numbers (#23056)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2026-04-20 19:34:11 +03:00
Mick 9a0fd2ff0c [diffusion] optimize: default to in-memory loading for URL/base64 image inputs (#23118) 2026-04-20 23:29:02 +08:00
Mick 0be6ab04dd [diffusion] refactor: LTX2.3 code cleanup (#23207) 2026-04-20 19:02:05 +08:00
YC Yen-Ching Tseng da62e90904 [AMD] Fix multimodal timeout issue : rocm7.2 PR Test (#23247) 2026-04-20 18:36:08 +08:00
YC Yen-Ching Tsengandbingxche cf4b84f839 [AMD] Update AMD workflow name (#23245)
Co-authored-by: bingxche <bingxche@amd.com>
2026-04-20 18:18:24 +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
Alex NailsandClaude Opus 4.7 bea4c895c1 [gRPC] Pass --experimental_allow_proto3_optional to protoc in build.rs (#23226)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-20 17:20:14 +08:00
69eb95f20c [AMD] Pin peft<0.19 in pyproject_other.toml to fix ROCm CI ImportError (#23161)
Co-authored-by: HAI <hixiao@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-19 23:43:56 -07:00
Liangsheng Yin a2d30d27fe wait for reap in kill_process_tree (#23213) 2026-04-19 23:36:33 -07:00
Bingxu Chen ab936ce694 Revert "perf: optimize PCG inductor path for FP8 models (#21734)" (#23159)
Feel free to PR again.
2026-04-19 23:32:50 -07:00
Kangyan-ZhouandClaude Opus 4.7 97baf17557 Fix test_modelopt_export using stale ModelConfig kwargs (#23214)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 23:18:09 -07:00
Kangyan-ZhouandClaude Opus 4.7 1ebe1c57ed [CI] Partition stage-a-test-cpu into 4 matrix shards (#23208)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 22:07:37 -07:00
Alex Nails 10e17cc55e [gRPC] Native gRPC server: proto + Rust crate scaffold + server args (#22736) 2026-04-20 12:39:35 +08:00
Baizhou ZhangandClaude Opus 4.6 c304d0d64d [Refactor] Deduplicate NSA utils.py into cp_utils.py for context parallel (#22914)
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-19 21:35:35 -07:00
Liangsheng Yin eb76aaba88 [core] Always-on StreamingSession in UnifiedRadixCache (#23202) 2026-04-19 21:19:43 -07:00
ShunkangzandShunkang e389a52cc8 Support allreduce fusion with cp (#21249)
Co-authored-by: Shunkang <182541032+Shunkangz@users.noreply.github.co>
2026-04-19 21:06:00 -07:00
Liangsheng Yin a7276b623e integrate streaming session into UnifiedRadixCache (#23145) 2026-04-19 20:47:41 -07:00
Kangyan-ZhouandClaude Opus 4.7 1d252803f5 fix(ci): repair path filters regressed by #21482 (#23201)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 20:34:57 -07:00
Thomasandronnie_zheng 3063d640dd [CI] Exclude diffusion-specific paths from main_package filter (#23053)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
2026-04-20 10:43:44 +08:00
1cff871c67 [Bugfix] Fix DeepEP timeout when compiling DeepGeMM in EP+DP+TP (#23185)
Co-authored-by: Byron Hsu <byronhsu@Byrons-MacBook-Pro.local>
Co-authored-by: Cheng Wan <ch-wan@users.noreply.github.com>
2026-04-19 17:36:11 -07:00
Liangsheng Yin d3ce664612 move session to python/sglang/srt/session (#23144) 2026-04-19 17:34:19 -07:00
7ca3566130 Multi platform Plugin (#21388)
Co-authored-by: root <root@tjzj-inf-sci-k8s-bzz2-0183.tjzj.baidu.com>
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
Co-authored-by: Alex Nails <alexj.nails@gmail.com>
Co-authored-by: root <root@tjzj-inf-sci-k8s-bzz2-0000.tjzj.baidu.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-04-19 17:23:51 -07:00
Cheng WanandClaude Opus 4.7 ebcc2b3eec ci: run weekly est_time update on Monday using p90 of last 15 runs (#23120)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-19 14:39:27 -07:00
inkcherry 4fa3482180 [Bugfix] Add missing http_worker_ipc in session error path (#22766) 2026-04-19 12:47:09 -07:00
billishyahao b74a9dd854 [AMD] fix tbo runtime error when initializing metadata for cuda graph (#22598) 2026-04-19 12:42:48 -07:00
YC Yen-Ching Tseng 32b7777f6c [AMD]Fix AMD multimodal-gen-test-2-gpu timeout by adding partition for standalone test (#23130) 2026-04-19 23:16:18 +08:00
6ecd6f84db [CI] Add per-job uv venv isolation and upgrade CI version to Cuda 13 (#23119)
Co-authored-by: Kangyan Zhou <zky314343421@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Co-authored-by: Alison Shao <a.shao@wustl.edu>
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-04-19 05:32:36 -07:00
Thomas Wang 03828f4205 [AMD] Reduce NSA indexer kernels (weights_proj, k-cache store kernel fusion) (#22850) 2026-04-19 00:18:11 -07:00
Kehan Li 2a327f0877 Fix Qwen3.5 video processing when passing video_data in "processor_output" format (#22431) 2026-04-19 00:04:01 +08:00
Xiaoyu Zhang cd6ad80c00 diffusion: add HunyuanVideo GroupNorm+SiLU fast path (#22814) 2026-04-18 23:38:49 +08:00
Xiaoyu Zhang c6a45fab64 Qwen3next flashinfer allreduce auto enable (#22664) 2026-04-18 22:32:41 +08:00
Yisheng Gong 4839cecbb0 [main] chore: add bias for base layer with lora (#22169) 2026-04-18 02:07:02 -07:00
amote-i ea20f1baa4 [NPU] [DOC] Update npu best practice docs to match latest code (#23077) 2026-04-18 14:17:00 +08:00
Mick 0d94c3366a [diffusion] feat: introduce ltx-2-two-stage device manager (#22869) 2026-04-18 11:04:33 +08:00
Xiaoyu Zhang 615d6c93b2 [codex] Add flashinfer TRTLLM backend for diffusion NVFP4 (#22717) 2026-04-18 09:06:28 +08:00
Lianmin Zheng 9c47bbad13 Clean up bench_one_batch warning and simplify norm dispatch (#23110) 2026-04-17 17:42:20 -07:00
Cheng WanandClaude Opus 4.7 5f7aee726a refactor(moe): de-duplicate triton MoE runner path into shared helpers (#23019)
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-04-17 17:05:13 -07:00
Yanbin Jiang fd7db0eace Update CI_PERMISSIONS (#23108) 2026-04-17 16:53:03 -07:00
R0CKSTAR 26ae7b8bd7 [MLX] Support radix cache (#21509)
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com>
2026-04-18 07:00:50 +08:00
Liangsheng Yin 09b689b407 Apply HF transformers patches from sglang init (#23103) 2026-04-17 15:37:51 -07:00
Liangsheng Yin 573e12a7fc Merge /get_load into /v1/loads (#23010) 2026-04-17 13:36:51 -07:00
Lianmin Zheng 44e67c6835 Remove deprecated double sparsity feature (#23009) 2026-04-17 13:33:12 -07:00
Liangsheng Yin 3df35ecc80 Lower TestPiecewiseCudaGraphQwen25VL gsm8k threshold to 0.80 (#23099) 2026-04-17 13:31:10 -07:00
andyluo7andAndy Luo 9df6107dca [AMD] Enable DFLASH speculative decoding on ROCm (#22342)
Signed-off-by: Andy Luo <andyluo7@users.noreply.github.com>
Co-authored-by: Andy Luo <andyluo7@users.noreply.github.com>
2026-04-17 13:10:14 -07:00
shuwennandZhangheng 90c76d665e [HiCache] fix: HiCacheFile component key suffixing (#22891)
Co-authored-by: Zhangheng <hzh0425@apache.org>
2026-04-17 13:06:28 -07:00
YC Yen-Ching Tseng 5d4e899477 [AMD] Fix AMD Multimodal Test - skip nvfp4 tests (#23045) 2026-04-17 09:02:39 -07:00
Jincong Chen 2bac219d0c [Perf] Precompute gemma_weight to avoid redundant add on every forward (#22673) 2026-04-17 23:37:41 +08:00
Xiaoyu Zhang 83c5119d01 [diffusion] CI: fix ModelOpt B200 CI artifact coverage (#22955) 2026-04-17 23:33:42 +08:00
Mick 5de89ea942 [diffusion] CI: fix auto-partition (#23076) 2026-04-17 22:37:24 +08:00