Commit Graph

Select branches

Hide Pull Requests

bot/update-est-time-20260928

dsv41-pd

dsv41-pd-visioncp

main

Mono Color

• e0e0cad6bc [Diffusion] Match rotary_embedding module name style (#19179) Xiaoyu Zhang 2026-02-23 21:02:34 +08:00
• 2717393681 [Refactor] Split rotary_embedding.py into a modular package (#19144) Xiaoyu Zhang 2026-02-23 20:05:29 +08:00
• 27d394a6a5 [NPU] bump sgl-kernel-npu to 2026.02.01.post2 (#19178) Even Zhou 2026-02-23 18:23:02 +08:00
• d80c884a27 Use single mma warp group for short q_len in FA to optimize decoding performance (#18985) Qiaolin Yu 2026-02-23 01:01:28 -08:00
• 6448de7e96 Reorganize topk logic to clean up code and expose logical experts (#16945) Junrong Lin 2026-02-23 16:30:57 +08:00
• 4f3dc1ef5b [ROCm] Use unreg path for custom all-reduce during CUDA graph capture (#19162) Yuzhen Zhou 2026-02-22 23:27:31 -08:00
• c3c1532820 [diffusion] feat: detect Flux2 custom VAE path from component_paths (#19170) Changyi Yang 2026-02-23 02:19:53 -05:00
• 6a999dbdf8 [AMD] ENV flags tuning and cleanup (#19176) HAI 2026-02-22 22:40:00 -08:00
• 42b1019881 Fix bench_one_batch_server by moving the print statements (#19175) Qiaolin Yu 2026-02-22 22:06:25 -08:00
• 3224836d8b Update rocm7.2 Dockerfile to install amdsmi for QuickReduce Initialization (#19091) Clint 2026-02-22 23:32:14 -06:00
• 2472e47d73 Revert "Refactor graph input buffers (#18991)" (#19173) Baizhou Zhang 2026-02-23 13:09:54 +08:00
• fa80b9beba [CI] Skip some subtests for tool call parser (#19172) Baizhou Zhang 2026-02-23 12:20:12 +08:00
• 0e670c36d6 fix(diffusion): enforce strict input_reference validation for T2V (#14825) Ratish PandXiaoyu Zhang 2026-02-23 09:34:06 +05:30
• 43f83525c0 Revert "[AMD] support two batch overlapping for mori ep #17953" (#19161) Baizhou Zhang 2026-02-23 01:19:23 +08:00
• 45095bac70 [diffusion] refactor: rename quantized model path server arg (#19142) Mick 2026-02-22 23:18:35 +08:00
• c6a99e43b9 Fix corrupted JSONL metrics file due to concurrent writes (#19011) Talor Abramovich 2026-02-22 14:33:27 +02:00
• 1f7a813051 [CI]Extend timeout for test_text_models_perf.py (#19155) Baizhou Zhang 2026-02-22 20:26:56 +08:00
• 7d4860bc5e [diffusion] CI: relax perf check threshold (#19154) Mick 2026-02-22 20:02:12 +08:00
• 87823722b3 [diffusion] chore: minor cleanups (#19123) Mick 2026-02-22 19:07:25 +08:00
• 1a1c768d44 Support kwargs and megatron core tensor parsing in dumper (#19138) fzyzcjy 2026-02-22 16:24:33 +08:00
• eddf193292 [DSv32] [GLM5] Improve Model Quality by Avoiding FP32 Precision Loss in weights_proj (#19041) Ziang Li 2026-02-22 00:20:51 -08:00
• 326b788ab4 Fix wrongly large dumped file and handle non intrusive hook reset in dumper (#19124) fzyzcjy 2026-02-22 16:20:08 +08:00
• c1f497e20e Enhance reset, states, http in dumper (#19095) fzyzcjy 2026-02-22 16:17:41 +08:00
• 4091b720c5 Support multi colocated dumper, named exp cleanup, argparse config (#19094) fzyzcjy 2026-02-22 16:16:15 +08:00
• 31f0c11405 Configure and call dumper in main SGLang logic (#19093) fzyzcjy 2026-02-22 16:14:27 +08:00
• cc63c99f11 Enhance hook mechanism in dumper (#19073) fzyzcjy 2026-02-22 16:13:38 +08:00
• fdf80b5031 Extract framework plugins in dumper (#19072) fzyzcjy 2026-02-22 16:10:43 +08:00
• e32b5364a2 Auto annotate context in dumper (#19071) fzyzcjy 2026-02-22 16:08:48 +08:00
• 8bc0751376 Support enabling partial non intrusive dump in dumper (#19069) fzyzcjy 2026-02-22 16:07:45 +08:00
• 0384c459a7 Support non-intrusive dumping in dumper (#19068) fzyzcjy 2026-02-22 16:04:02 +08:00
• 5eccc3cff9 Refactor dumper and change on_forward_pass_start API (#19065) fzyzcjy 2026-02-22 16:03:27 +08:00
• eccee4c48e [PD] Change bootstrap_room metadata dtype from int64 to uint64 (#19141) Shangming Cai 2026-02-22 14:20:16 +08:00
• 5995bfec63 [Qwen3-Next] Enable fused_qkvzba_split_reshape_cat also for prefill (#18917) YAMY 2026-02-21 21:57:17 -08:00
• 8cf003c44b Fix spec v2+dp attention in nsa backend (#19134) Qiaolin Yu 2026-02-21 21:46:15 -08:00
• 8612358ee9 [BUG] [DLLM] Missing max_running_requests value (#18740) Bhavneek Singh 2026-02-22 14:38:56 +09:00
• ae62898ffb [diffusion] quant: adapt FP8 linear to sgld and support quant in flux (#17023) 3 people 2026-02-22 12:55:28 +08:00
• cef353f338 [Fix] Quick fix for int32 overflow in Mooncakes' send_kvcache_slice (#19076) YAMY 2026-02-21 20:00:33 -08:00
• b2d8cc8cf0 Fix dev Docker build OOM on ARM64 cu13 by adding docker system prune (#18947) Kangyan-ZhouandClaude Opus 4.6 2026-02-22 10:29:31 +08:00
• 4653939cda Revert "[jit kernel] Support per_token_group_quant_8bit jit kernel" (#19131) Liangsheng Yin 2026-02-21 15:54:24 -08:00
• 1f2da824dd [Benchmark] Remove re-exports from bench_serving.py (#19130) Liangsheng Yin 2026-02-21 14:30:30 -08:00
• f158869c2c [Refactor] Benchmark Phase 1: extract utils and datasets from bench_serving (#19077) Ratish PandXuchun Shang 2026-02-22 03:20:11 +05:30
• 3fb457b103 Tiny rename cuda_graph tests to piecewise_cuda_graph (#19128) Liangsheng Yin 2026-02-21 13:46:01 -08:00
• 7b0fb43c7a [FlashInfer] Switch FlashInfer allreduce fusion to unified API (#18341) Mohammad Miadh Angkad 2026-02-22 00:07:16 +08:00
• bf36aa4c31 [sgl] view could hold the memory too long and introduced large memory (#19109) Bi Xue 2026-02-21 07:40:56 -08:00
• 677b66af80 fix KimiK2Detector regex patterns with re.DOTALL (#19120) Xinyuan Tong 2026-02-21 09:13:08 -05:00
• 4a362a0e04 fix tool handling in OpenAIServingChat (#18996) Xinyuan Tong 2026-02-21 09:07:09 -05:00
• 66497ab0aa [Diffusion] Restruct and clean Diffusion rotary embedding (#19064) Xiaoyu Zhang 2026-02-21 21:41:47 +08:00
• d8d0208c63 [Feature] rewrite rope kernel; remove flashinfer dependencies (#18844) DarkSharpnessandgemini-code-assist[bot] 2026-02-21 21:32:40 +08:00
• 6503f94211 [diffusion] feat: support passing component path via server args (#19108) Mick 2026-02-21 21:22:47 +08:00
• c36a10aabb Tiny update pull-requests permission of release-branch-cut.yml (#19121) Baizhou Zhang 2026-02-21 20:14:31 +08:00
• cc451671b5 [FEAT] Add Anthropic compatible API endpoint (#18630) Xinyuan Tong 2026-02-21 06:37:38 -05:00
• b89ca65789 [diffusion] refactor: reduce redundancy and improve stage api (#19060) Mick 2026-02-21 16:35:47 +08:00
• 33c33a7de9 [Quantization] Support config.json quantization_config format, fix exclude_modules matching, and fix KV cache scale loading for Nemotron (#18546) danielafrimi 2026-02-21 10:14:29 +02:00
• e239f8aa85 Remove error dllm and diffusion doc in basic_useage (#19105) 赵晨阳 2026-02-20 20:28:00 -08:00
• 51b3ed02ca Fix bug in symm mem pre-allocation default (#19082) Nicolas Castet 2026-02-20 21:51:28 -06:00
• afd91e8782 [DSv32] Fix MTP and CP compatability (#19062) Vladislav Nosivskoy 2026-02-21 06:10:34 +03:00
• 463baafe10 [Auto Sync] Update batch_invariant_ops.py (20260221) (#19098) 3 people 2026-02-20 18:27:31 -08:00
• 2928dfb8fa [Auto Sync] Update bench_one_batch_server_internal.py (20260221) (#19097) 3 people 2026-02-20 18:19:14 -08:00
• 84c67c8be0 Refactor graph input buffers (#18991) Cheng Wan 2026-02-20 18:09:31 -08:00
• b2573fe426 Upd: CODEOWNERS (#19055) HAIandLiangsheng Yin 2026-02-20 15:51:53 -08:00
• 4bffd3a232 [GPT-OSS] support fp8 online quantization for gpt-oss bf16 (#18988) Minglei Zhu 2026-02-20 14:16:57 -08:00
• 96bae2355e Add generated-shared-prefix dataset in bench_one_batch (#18986) Qiaolin Yu 2026-02-20 13:33:10 -08:00
• ab18734375 [feat] feat: support swa in trtllm_mha (#18970) 0xNullPath 2026-02-21 01:39:29 +08:00
• fbb6098487 [AMD] support two batch overlapping for mori ep (#17953) 5 people 2026-02-21 00:45:55 +08:00
• 38ee749dd9 Fix adjust_num_token_non_padded_for_attn_tp returning CPU tensor (#19051) Cheng Wan 2026-02-20 07:23:38 -08:00
• 3358ba8945 [Fix] Run FlashInfer autotune on non-default stream for NCCL 2.29+ compatibility (#18987) Nicolas Castet 2026-02-20 09:21:38 -06:00
• 52852404c8 [Fix] DO NOT skip save_kv_cache for dllm (#19020) DarkSharpness 2026-02-20 23:20:29 +08:00
• f23a23cc05 Fix NSA FP8 KV cache path for both-trtllm MHA one-shot (#18931) Mohammad Miadh Angkadandrainj-me 2026-02-20 22:00:09 +08:00
• 8d789b5c3d [diffusion] feat: support nunchaku for Z-Image-Turbo and flux.1 (int4) (#18959) Mick 2026-02-20 21:16:08 +08:00
• 7d953440ec [jit kernel] Support per_token_group_quant_8bit jit kernel (#18905) Yuan Luoandluoyuan.luo 2026-02-20 21:01:05 +08:00
• 38a69652e6 [diffusion] logging: log available mem when each stage starts in debug level (#18998) Mick 2026-02-20 19:57:06 +08:00
• 0d20cf5a66 Fix lint on main (#19054) fzyzcjy 2026-02-20 15:45:24 +08:00
• 77fdb6af81 feature: docker patch workflow (#19025) Douglas Yang 2026-02-19 23:37:40 -08:00
• b59a22f781 fix lint on main (#19052) Cheng Wan 2026-02-19 23:30:57 -08:00
• b0786cdf94 [AMD] Replace msgpack with msgspec in MORI-IO (#19007) Duyi-Wang 2026-02-20 15:04:15 +08:00
• 8541b1118d [Fix][Qwen3.5] Pass max_mamba_cache_size to mamba pool in disaggregation decode path (#19002) YAMY 2026-02-19 22:31:26 -08:00
• 295bc17576 Feature/sdar support (#19044) 4 people 2026-02-20 13:58:15 +08:00
• 046ef0aa35 Support using SGLang port in dumper (#19038) fzyzcjy 2026-02-20 12:30:24 +08:00
• 2fecc2c075 Support resetting and enhance HTTP endpoints for dumper (#19046) fzyzcjyandYueming Yuan 2026-02-20 12:29:09 +08:00
• 503bf3047a Enhance configure and env parsing in dumper (#19034) fzyzcjy 2026-02-20 12:28:10 +08:00
• df995aab56 Support filtering labels in dumper (#19018) fzyzcjy 2026-02-20 12:27:12 +08:00
• 261bca3c58 Support captured dump output and console output control in dumper (#19017) fzyzcjy 2026-02-20 12:26:24 +08:00
• fc1500adc6 Hint users when wrongly execute it with partial ranks in dumper (#19014) fzyzcjy 2026-02-20 12:25:54 +08:00
• b41d412c3d Support cleanup previous dumps in dumper (#19013) fzyzcjy 2026-02-20 12:25:21 +08:00
• 13a4a0406e Fix flashinfer autotune to only wrap run_once() (#19004) Cheng Wan 2026-02-19 20:02:21 -08:00
• 64bca5315f Fix long prompt KV allocation by falling back to torch native APIs when exceeding Triton tensor limit (#18250) Cheng Wan 2026-02-19 19:15:05 -08:00
• 99df920cdb Register tensors with symmetric memory for qwen (#18643) Nicolas Castet 2026-02-19 19:32:32 -06:00
• 73a7f0d049 Revert "Add SDAR model support" (#19032) Cheng Wan 2026-02-19 16:03:56 -08:00
• db34c1cbfb Tiny remove duplicate coredump env injection (#19023) Liangsheng Yin 2026-02-19 13:26:30 -08:00
• 5ff5aa6923 [spec v2]Fix torch gc of future indices (#18958) Liangsheng Yin 2026-02-19 11:38:25 -08:00
• 44ab752b7a Add SDAR model support (#18318) 4 people 2026-02-20 03:20:32 +08:00
• 3207427d6d [diffusion] CI: enable warmup as default (#19010) Mick 2026-02-19 23:27:23 +08:00
• d73f06f091 [diffusion] chore: improve memory usage on consumer-level GPU (#18997) Mick 2026-02-19 21:59:49 +08:00
• 963def7f26 Move lora request validation to tokenizer_manager from server (#18962) satyamk7054andSatyam Kumar 2026-02-19 05:03:19 -08:00
• d07e8aa4a3 [Diffusion] [NPU] Enable profiler on NPU (#17807) Makcum888e 2026-02-19 15:33:51 +03:00
• e21fc78dbd [diffusion] fix: fix rank used in parallel executor when enable_cfg_parallel is false (#18975) Prozac614anddaiweitao 2026-02-19 20:12:24 +08:00
• 19aa19b111 [diffusion] refactor: refactor diffusion triton kernels (#18966) Xiaoyu Zhang 2026-02-19 17:03:44 +08:00
• 48642d5384 [RadixTree][4/N Refactor]: Move available_and_evictable_str to individual radix cache classes (#17852) pansicheng 2026-02-19 17:03:15 +08:00
• 82a0bafc1c Feat/add fi selective state update kernel call (#18070) shaharmor98 2026-02-19 10:56:06 +02:00
• 0be30d4b0d Fix PCG MoE Error (#17739) Yuwei An 2026-02-19 00:48:06 -08:00