Commit Graph

7673 Commits

Author SHA1 Message Date
Yineng Zhang
ef1ab2302a [Auto Sync] Update tool_chat_template_deepseekv31.jinja (20251210) (#14837)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Jue Wang <zjuwangjue@gmail.com>
2025-12-10 10:56:24 -08:00
Mick
d659873762 [diffusion] CI: use unified sampling_params for CI (#14045) 2025-12-11 01:18:56 +08:00
Mick
6c5ebc0ef7 [diffusion] parallel: pad tokens for video models under sp (#14833) 2025-12-11 01:15:37 +08:00
Ke Bao
5b5571a8da Apply back moe_sum_reduce for fused_marlin_moe (#14829) 2025-12-11 00:39:41 +08:00
Alison Shao
1698c2341b [CI] Reduce stage-b auto-partition from 4 to 2 (#14769)
Co-authored-by: Liangsheng Yin <lsyincs@gmail.com>
2025-12-11 01:32:33 +09:00
fzyzcjy
3d82c0f17f [model-gateway] support engine response http status statistics in router (#14712) 2025-12-10 08:30:53 -08:00
fzyzcjy
617e9b3bf8 [model-gateway] support customizing Prometheus duration buckets (#14716) 2025-12-10 08:30:03 -08:00
Li Jinliang
83e35a7c29 [diffusion] doc: fix tiny typo in multimodal_gen/README.md (#14830) 2025-12-11 00:27:25 +08:00
Simo Lin
2543666c8e [model-gateway] add anthropic message api spec (#14834) 2025-12-10 08:26:51 -08:00
Alison Shao
f732f8ea57 Fix CI registry scan to only check test/registered directory (#14812) 2025-12-11 01:09:03 +09:00
Liangsheng Yin
503880dbbe [CI] fix UT success check in test_eagle_infer_beta_dp_attention.py (#14831) 2025-12-11 01:00:50 +09:00
liupeng374
b8cfa02c01 [NPU] bug fix for mtp and w4a8 (#14806) 2025-12-10 22:55:13 +08:00
fzyzcjy
d85fecb536 Tiny fix incorrect worker removal command (#14822) 2025-12-10 22:29:39 +08:00
fzyzcjy
6634f67bd5 Fix router keep nonzero metrics after worker is deleted (#14819) 2025-12-10 22:29:30 +08:00
fzyzcjy
5eccaf7737 Support HTTP response status code prometheus metrics (#14710) 2025-12-10 22:28:57 +08:00
Wenyi Xu
d7f6320bb8 [model-gateway] Dynamically Populate Tool Call Parser Choices (#14807) 2025-12-10 06:04:22 -08:00
ybyang
766476f52a [SMG-GO] implement a Go SGLang Model Gateway - OpenAI Compatible API Server (#14770) 2025-12-10 06:03:28 -08:00
Xiaoyu Zhang
12b7a4fab0 [diffusion] performance: refactor diffusion fuse qkv and apply to qwen-image (#14793) 2025-12-10 18:55:41 +08:00
Yuhao Yang
02f1e81e2d Revert "fix: checking if tokenizer is in cache before downloading from HF" (#14808) 2025-12-10 01:14:35 -08:00
Prozac614
908c7186af [diffusion] CI: Add LoRA support to diffusion server configuration and test cases (#14697) 2025-12-10 16:51:47 +08:00
Yuan Luo
03836d85d2 [GLM-4.6V] Support Pipeline Parallelism for GLM-4.6V & GLM-4.1V (#14720)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-10 16:40:12 +08:00
Mick
87dbdddc93 [diffusion] profile: early exit when enough steps are captured to reduce the size of the trace file (#14803) 2025-12-10 16:11:22 +08:00
b8zhong
56e5c07424 fix b200 fa4 ci (#14788) 2025-12-10 00:03:43 -08:00
yrk111222
6c9c8da64d fix: add missing logic for SGLANG_USE_MODELSCOPE variable (#14794) 2025-12-10 15:49:34 +08:00
Peng Zhang
21028b5507 [RL] support weight reload for low-bit rollout (#9650)
Co-authored-by: Hecate0821 <hec4te0821@gmail.com>
Co-authored-by: eternally-z <zzywzj@gmail.com>
Co-authored-by: Wilboludriver <wilbolu@outlook.com>
Co-authored-by: Wilbolu <81792854+Wilboludriver@users.noreply.github.com>
Co-authored-by: Ke Bao <ispobaoke@gmail.com>
2025-12-10 15:44:01 +08:00
b8zhong
b0a25d0913 fix b200 ci (#14786) 2025-12-09 23:08:41 -08:00
Yuhao Yang
793c98afaf handling incomplete rope_scaling config ci after transformers upgrade (#14784) 2025-12-09 22:56:16 -08:00
TomerBN-Nvidia
b1cbfce612 fix server args bug (#14725) 2025-12-09 21:05:05 -08:00
Alison Shao
b0f531ad28 Fix VLM accuracy thresholds for nightly tests (#14777) 2025-12-09 20:59:23 -08:00
Alison Shao
01835998e1 fix: race condition between validation and download locks (#14761) 2025-12-09 20:36:54 -08:00
Lianmin Zheng
4285e99da7 [Auto Sync] Update data_parallel_controller.py, detokenizer... (20251209) (#14759)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
2025-12-09 18:38:38 -08:00
ShawnY112358
f077436831 [fix] Fix issues for in-flight weight updates (#14064)
Co-authored-by: 赵晨阳 <zhaochen20@outlook.com>
2025-12-09 18:12:19 -08:00
Alison Shao
5e8f544d1b Disable 8-gpu-b200 runner in PR tests (#14768) 2025-12-09 17:47:54 -08:00
Douglas Yang
c8d74feb06 fix: adding rate limit warning at verify token permission stage (#14756) 2025-12-09 17:21:04 -08:00
Liangsheng Yin
cbc7dcdaa7 Re-add the API serving timing metrics. (#14744)
Signed-off-by: zhanghaotong <zhanghaotong.zht@antgroup.com>
Co-authored-by: zhanghaotong <zhanghaotong.zht@antgroup.com>
2025-12-10 10:17:48 +09:00
MingxuZh
a6dc7d2932 [ci]: Enable the new hf API (#14687) 2025-12-09 17:07:51 -08:00
Simo Lin
390406c46c [model-gateway] release gateway 0.2.4 (#14763) 2025-12-09 16:34:29 -08:00
Ethan (Yusheng) Su
0c63fb9420 [Feature] Add LoRA support for embedding layers (#14177)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
Co-authored-by: Beichen-Ma <bm685@cornell.edu>
2025-12-09 15:53:33 -08:00
Simo Lin
9ad02b799d [Perf] Optimize radix tree for cache-aware load balancin (#14758) 2025-12-09 15:35:29 -08:00
Lianmin Zheng
18bd8e8d6d Improve CI by trying a warmup before unit tests (#14669) 2025-12-09 15:17:59 -08:00
Lianmin Zheng
036e64dafa move multi-item scoring functions in tokenizer manager into a separate file (#14740) 2025-12-09 14:47:06 -08:00
Douglas Yang
7c6fb3aa2d fix: making rate limit a warning instead of error (#14753)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-09 13:41:09 -08:00
Douglas Yang
8b0b6a45c8 fix: checking if tokenizer is in cache before downloading from HF (#14698) 2025-12-09 13:08:07 -08:00
b8zhong
55504df2f7 Add FP8 Blockwise GEMM Backend Flag --fp8-gemm-backend (#14379) 2025-12-09 12:05:56 -08:00
Simo Lin
73df7a4e8d [SMG] perf: optimize tokenizer for reduced CPU and memory overhead (#14752) 2025-12-09 11:41:13 -08:00
Simo Lin
8b98bb768c [model-gateway] optimize core modules (#14751) 2025-12-09 10:54:07 -08:00
Yuhao Yang
15bc8cbd74 fix rope parameter initialization error caused by transformers v5.0 update (#14745) 2025-12-09 10:51:26 -08:00
yudian0504
9496f12d00 [Model] Add PaddleOCR-VL Model Support (#12953)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-12-09 10:16:02 -08:00
Lianmin Zheng
ab0048793c Revert "[Feat] Add received_time in serving_base" (#14743) 2025-12-09 06:52:27 -08:00
blahblah
6ec77680df [diffusion] feat: support comparing batch perf (#14738)
Co-authored-by: shuxiguo <shuxiguo@meituan.com>
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-12-09 22:48:52 +08:00