Commit Graph

Select branches

Hide Pull Requests

cch/megamoe-rc-v0.1

Mono Color

• 8b1ab4aaf9 Support agent-friendly output formats in dump comparator (#19275) fzyzcjy 2026-02-25 09:40:33 +08:00
• d7578ce279 Implement simplest dump comparator v2 (#19274) fzyzcjy 2026-02-25 09:37:21 +08:00
• 9cec98b445 [diffusion] fix: shard timestep_proj in sequence-sharded ti2v (#19237) wxy 2026-02-25 09:33:45 +08:00
• 0ede5c54a8 [diffusion] logging: improve request and component load logs (#19253) Mick 2026-02-25 09:32:36 +08:00
• 15f2e36fb9 [NPU] forward_npu uses native impl by default in MultiPlatformOp (#18545) silencejade 2026-02-25 09:16:09 +08:00
• b9cf1563de [ROCm] Optimize Deepseek R1 on MI300X (#18242) Chen, Zhentao 2026-02-25 09:01:14 +08:00
• f1088beb6a [NPU]Optimization of forward_npu for UnquantizedFusedMoEMethod (#13158) Vladimir221 2026-02-25 03:55:20 +03:00
• d7a03c7ebf [MoE Refactor] Refactor FlashInferFusedMoE into FusedMoE and flashinfer_trtllm.py (#19266) Jonah Bernard 2026-02-24 19:47:53 -05:00
• 750ecf4a45 Add server CUDA graph warmup CI step for cold H200 nodes (#19201) Alison Shao 2026-02-24 16:07:01 -08:00
• c193a52fa2 [AMD] DSR1/V3 use fp8 bmm in MLA for MI300X (#18624) Chen, Zhentao 2026-02-25 07:33:33 +08:00
• 152560d1b9 [PCG] add pcg CI test for gpt-oss model (#18961) Kaiqi Jin 2026-02-24 15:32:34 -08:00
• ae6f6e1495 [Refactor] Benchmark: Add typed DatasetArgs/Loader registry and CPU dataset unit tests (#19147) Ratish P 2026-02-25 01:52:01 +05:30
• 65de904130 feature: adding image retag workflow (#19265) Douglas Yang 2026-02-24 11:33:05 -08:00
• 0c224c3c62 docs: Embed release lookup tool into Sphinx documentation site (#19264) shuwenn 2026-02-25 03:11:27 +08:00
• 38f25e802d Fix/deepseek readme link (#19258) Alec Leng 2026-02-24 13:46:56 -05:00
• a06425184f [Fix] remove redundant +1 when getting tail_str for Req (#18584) Glen Liu 2026-02-24 13:35:26 -05:00
• 9bce3b040c [diffusion] [NPU] Update perf baselines (#19227) Makcum888e 2026-02-24 21:15:16 +03:00
• e6ad58e5da [diffusion] fix: webui not return data (#19244) Zihao Wang 2026-02-24 23:39:06 +08:00
• 1efc33c640 [diffusion] refactor: remove enums and unify attention backends (#19149) Adarsh Shirawalmath 2026-02-24 18:51:23 +05:30
• ea1bc1c578 [diffusion] feat: optimize all_to_all (#19157) triple-mu 2026-02-24 21:20:10 +08:00
• e3a234478c [NPU][Docs] Add Commonly Used Environment Variables for on NPU (#18556) husf 2026-02-24 20:05:33 +08:00
• 31c7dc9d99 [VLM] Introduce FlashInfer CUDNN Prefill as ViT Backend (#19003) Yuan Luo 2026-02-24 19:49:22 +08:00
• 1a83b2c15d fix: fix the bug blocking completion template application (#17010) xdtbynd 2026-02-24 18:50:08 +08:00
• 6e54361608 Refactor CUDA graph input buffers with shared buffer pool (#19180) Cheng Wan 2026-02-24 02:24:40 -08:00
• 94946764a4 bugfix: The default value of the environment virable is None, so that… (#18309) jianzhao-xu 2026-02-24 18:10:21 +08:00
• fcfd964d7d [diffusion] model: LTX-2 Support PR3 (#19151) GMI Xiao Jin 2026-02-24 00:55:28 -08:00
• b2166a2f33 fix(gateway): pin internal crate dependencies to exact versions (#19224) Simo Lin 2026-02-23 22:35:47 -08:00
• 88a7e48108 fix(grpc): handle embedding requests in _handle_batch_output (#19221) Simo Lin 2026-02-23 22:32:16 -08:00
• 2e053d6eb6 [diffusion] quant: support quant for all dits (#19156) Mick 2026-02-24 14:20:54 +08:00
• 4f25a48d7a support xverse_moe on npu fy 2026-02-24 14:11:20 +08:00
• 5e80027ac7 [PD-Disagg] Support FAKE transfer backend for more cases (#19215) Liangsheng Yin 2026-02-23 20:50:43 -08:00
• 02a646ba4e [CI]: add CI permission (#19214) Ratish P 2026-02-24 10:07:55 +05:30
• d8ef33a551 bugfix: prioritize init_npu_backend to fix various initialization bugs (#17652) jianzhao-xu 2026-02-24 12:25:20 +08:00
• 59e7ea99c5 fix: release docker worker wrong args (#19207) Douglas Yang 2026-02-23 19:51:06 -08:00
• feb041f4e5 [PD-Disagg] Improve type hints across all conn.py (#19208) Liangsheng Yin 2026-02-23 19:44:23 -08:00
• edba96b98a fix(docker): migrate ROCm Dockerfiles from setuptools-rust to maturin (#19210) Simo Lin 2026-02-23 19:00:05 -08:00
• ea7ef63e6d [PD-Disagg] Deduplicate common KVManager methods into CommonKVManager (#19205) Liangsheng Yin 2026-02-23 18:34:21 -08:00
• 8aeb16f3fc fix: add missing blank line after docstring in serving_transcription.py (#19206) Kangyan-Zhou 2026-02-23 18:29:38 -08:00
• 581bf53e03 Whisper model support & /v1/audio/transcriptions endpoint & benchmark (#16983) Xinyuan Tong 2026-02-23 20:28:37 -05:00
• 3a11e7dad9 fix: patch docker image fixes (#19100) Douglas Yang 2026-02-23 16:34:29 -08:00
• d160c5b9bb [PD-Disagg] Unify prefill info data transition flow, all with PrefillServerInfo (#19195) Liangsheng Yin 2026-02-23 16:15:20 -08:00
• 9fac90d85d [CI] Tiny enhance the dp attention load blance benchmark (#19194) Liangsheng Yin 2026-02-23 14:33:32 -08:00
• 672b666057 add new ci user (#19133) narutolhy 2026-02-23 12:48:04 -08:00
• 2aa3fe394e [CI] fix the teardown output of disaggregation test (#19193) Liangsheng Yin 2026-02-23 12:41:03 -08:00
• 2274bfebb1 [PD-Disagg] Support query dp rank from bootstrap server. (#19168) Liangsheng Yin 2026-02-23 10:59:30 -08:00
• 2cdde5d4ab [Kernel Slimming] Migrate AWQ marlin repack kernel to JIT (#18949) Linyu Wu 2026-02-23 22:05:27 +08:00
• 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 P 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) fy1214 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-Zhou 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 P 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) DarkSharpness 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