Commit Graph

11116 Commits

Author SHA1 Message Date
siyu
078d96213a [FEAT] optimize tensor zmq transfer for multimodal inputs (#13592)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
Co-authored-by: Yuhao Yang <47235274+yhyang201@users.noreply.github.com>
2026-01-03 12:23:23 +08:00
Douglas Yang
8b111b20c3 feature: improvements to CI failure monitor (#16272) 2026-01-02 20:09:41 -08:00
b8zhong
74a166cb86 [Fix] Only add SM90 and SM100 to check for auto-enabling TRT Allreduce Fusion (#16283) 2026-01-03 11:43:17 +08:00
triple-mu
888e126ac9 [diffusion] comment: fix typo (#16257)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-03 11:42:04 +08:00
Baizhou Zhang
bb23a8fe77 [Tiny]Remove progress bar for fp8 ue8m0 quant when unneeded (#16177) 2026-01-03 10:54:12 +08:00
sunxxuns
8b869e326c [AMD] feat: add DLLM support for AMD GPUs with LLaDA2 testing (#15560) 2026-01-03 10:41:11 +08:00
Alison Shao
6256936d09 Fix: Allow build-wheels to run when target_stage is set (#16324) 2026-01-02 17:58:11 -08:00
Lianmin Zheng
62f73a8c81 [Auto Sync] Update engine.py (20260102) (#16317)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2026-01-02 17:29:40 -08:00
Ke Bao
7c1b4b1c4c Support swa allocator page size > 1 (#16296) 2026-01-03 08:49:47 +08:00
Simo Lin
31ed68e7c1 [model-gateway] address embedding similarity threshold in ut (#16321) 2026-01-02 16:46:55 -08:00
Chang Su
24c91001cf [model-gateway] code clean up in tokenizer register step workflow (#16316) 2026-01-02 16:05:10 -08:00
Chang Su
c4edcac6d7 refactor(core): remove get_by_model_fast alias in worker_registry (#16313) 2026-01-02 16:04:23 -08:00
Chang Su
e93433892b refactor(steps): consolidate duplicate strip_protocol function (#16318) 2026-01-02 16:02:42 -08:00
Chang Su
a2d4f58a96 fix(http): use 504 Gateway Timeout for upstream timeouts (#16320) 2026-01-02 16:01:44 -08:00
Chang Su
f66b091699 refactor(http): improve pd_types.rs documentation and style (#16319) 2026-01-02 16:01:11 -08:00
Chang Su
2f623368ab refactor(core): use idiomatic .min() in calculate_delay (#16314) 2026-01-02 15:46:13 -08:00
Chang Su
bd9a2ced47 refactor(core): use thiserror for WorkerError (#16315) 2026-01-02 15:33:07 -08:00
Chang Su
0ca417d9ae chore(core): remove unused serde_json import in worker.rs (#16312) 2026-01-02 15:31:41 -08:00
sunxxuns
30cfb687fa fixed amd multimodal CI failures caused by refactor in #15812 #15813 (#16287) 2026-01-02 14:55:42 -08:00
Chenxi Li
b7c7e03d93 Fix crash dump replay script for image data replay (#16277) 2026-01-02 13:42:22 -08:00
Alison Shao
f0195627a9 Fix sgl-kernel jobs to skip when target_stage is specified (#16308) 2026-01-02 12:49:26 -08:00
Simo Lin
d401d23876 [model-gateway] Add embedding correctness test comparing against HuggingFace (#16092)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2026-01-02 10:58:20 -08:00
Alison Shao
17041f4673 Enable /rerun-stage slash command to work on fork PRs (#16128) 2026-01-02 10:36:12 -08:00
Baizhou Zhang
f07e76b229 Multiple refactors of DeepSeek V32 and context parallel (#16305) 2026-01-03 02:21:22 +08:00
Xiaoyu Zhang
1cfd2b2ded [diffusion] chore: remove redundant ulysses nccl warmup (#16301) 2026-01-03 00:19:35 +08:00
Yongfei Xu
0d244116d2 [DeepSeek v3.2] opt Context Parallelism: support fused moe, multi batch and fp8 kvcache (#13959) 2026-01-02 23:49:14 +08:00
Changyi Yang
0eae831797 [diffusion] fix: Increase text length from 256 to 1024 in Qwen-Image (#16248)
Co-authored-by: Mick <mickjagger19@icloud.com>
2026-01-02 23:25:31 +08:00
Ke Bao
c483a5f45f Tiny adjust hybrid swa handling (#16292) 2026-01-02 23:11:23 +08:00
Mick
f26f6c2c99 [diffusion] fix: make lora compatible with layerwise-offload (#16298)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-01-02 22:33:26 +08:00
roikoren755
b021332339 [NemotronH] Add latent MoE support (#16227)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-01-02 22:08:58 +08:00
Mick
5062537b67 [diffusion] feat: support lightweight e2e warmup for benchmarking (#16213) 2026-01-02 20:10:27 +08:00
Ke Bao
698629d1f2 Add swa page table to FA3 backend forward metadata (#16267) 2026-01-02 20:00:43 +08:00
Qiaolin Yu
dd93e4451c Support returning customized info (#16144) 2026-01-02 15:32:18 +08:00
Yuhao Yang
6c8587b5db [diffusion] fix: align negative prompt with official readme for new model (#16222) 2026-01-02 15:20:56 +08:00
Yinghai Lu
027042604d [distributed] Clean up MoE groups in destroy_model_parallel (#15345) 2026-01-02 14:45:14 +08:00
Xiaoyu Zhang
bd48ad5e6b [Diffusion] Fix broken ring_attention when use upstream fa3 (#16270) 2026-01-02 14:33:12 +08:00
fzyzcjy
749736ba95 Tiny fix single-gpu dumper and add tests for dumper (#16285) 2026-01-02 13:30:09 +08:00
Nan Jiang
7254986342 [VLM] feat: true on policy for vlm + fsdp (#14636)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
2026-01-01 16:54:39 -08:00
fzyzcjy
00562ee14a Support cache eviction for Manual Policy (#16263) 2026-01-02 08:52:01 +08:00
Hudson Xing
d7a8257ba5 docs: remove outdated TODO in GLM-4.7 MoE detector test (#16265) 2026-01-01 10:25:23 -08:00
DarkSharpness
f6f7af4068 [Refactor] Clean up custom op (#15995) 2026-01-01 21:41:56 +08:00
DarkSharpness
a3b1e8ef3d [Feature] add aligned_vector type for JIT kernel (#16162) 2026-01-01 21:40:05 +08:00
fzyzcjy
db499e1889 Tiny add filter, support duplications, add visualizations, fix error and robustness for dump comparator (#16262) 2026-01-01 17:47:00 +08:00
fzyzcjy
6cf3a6dd69 Support HTTP control for dumper (#16261) 2026-01-01 17:40:17 +08:00
fzyzcjy
90e24f5c31 Tiny add filter, dump dict, failable save to dumper (#16260) 2026-01-01 17:35:38 +08:00
Mick
21de3e1406 [diffusion] webui: tiny fix loading output image (#16251) 2026-01-01 14:34:49 +08:00
Lianmin Zheng
e4c1e441af Fix deprecation warning of sre_parse for python 3.13 (#16247) 2025-12-31 21:25:09 -08:00
Alison Shao
b5af283b1c ci: increase stage-b-test-small-1-gpu partitions from 4 to 5 (#16250) 2026-01-01 12:08:31 +08:00
Kangyan-Zhou
130c6911f8 Add a GH action for cherrypick (#16243) 2025-12-31 20:05:38 -08:00
1874.
e0e5084802 Fix parse args from file(#13911) (#14085)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2026-01-01 11:37:33 +08:00