Cheng Wan
|
97cd38e58d
|
Skip weight loading in deepgemm compilation (#11312)
|
2025-10-07 21:52:46 -07:00 |
|
Cheng Wan
|
3c06b673af
|
[8/N] MoE Refactor: deprecate EPMoE (#11211)
|
2025-10-07 21:51:41 -07:00 |
|
Adarsh Shirawalmath
|
7c3f07dbcb
|
[Feature] Add /tokenize and /detokenize OpenAI compatible endpoints (#9545)
|
2025-10-08 12:38:48 +08:00 |
|
Chang Su
|
edd86b8853
|
[router][grpc] Refactor chat handler in grpc/ to use centralized orchestrator (#11314)
Co-authored-by: Simo Lin <linsimo.mark@gmail.com>
|
2025-10-07 20:50:20 -07:00 |
|
Liangsheng Yin
|
4b4dc132fa
|
Rename ngram_utils -> ngram_info (#11316)
|
2025-10-08 11:49:46 +08:00 |
|
YAMY
|
5a9170d993
|
Optimize copy_kv_cache for spec decoding (#11126)
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
|
2025-10-08 10:43:30 +08:00 |
|
Xinyuan Tong
|
c4d77774e1
|
update sampling_params documentation with defaults (#11315)
|
2025-10-07 18:36:26 -07:00 |
|
DarkSharpness
|
832c84fba9
|
[Chore] Update xgrammar 0.1.24 -> 0.1.25 (#10710)
|
2025-10-07 18:22:28 -07:00 |
|
Mick
|
64d1505c0a
|
ci: unify the model launch method of nightly ci (#11230)
|
2025-10-07 18:13:14 -07:00 |
|
cctry
|
f3764c26a3
|
Clean match_prefix and prepare_for_extend for mem cache V2 (#11200)
|
2025-10-07 17:54:18 -07:00 |
|
Chang Su
|
7ba3de0e92
|
[oai serving chat] Add argument --sampling-defaults and fix ChatCompletionRequest defaults (#11304)
|
2025-10-08 00:36:05 +00:00 |
|
Simo Lin
|
fde9b96392
|
[router] cleanup worker health check to return early (#11310)
|
2025-10-07 16:53:10 -07:00 |
|
Chang Su
|
f094e0a490
|
[router][grpc] Fix request_id extraction when n > 1 (#11311)
|
2025-10-07 19:27:56 -04:00 |
|
Keyang Ru
|
4ed67c27e3
|
[router] support Openai router conversation API CRUD (#11297)
|
2025-10-07 15:31:35 -07:00 |
|
Bowen Bao
|
cd4b39a900
|
[quantization] Properly ignore quantization for layers excluded in quant_config (#11205)
|
2025-10-07 14:06:05 -07:00 |
|
Chang Su
|
420c99acfe
|
[router][grpc] Fix error message format in grpc chat handler (#11307)
|
2025-10-07 13:54:02 -07:00 |
|
Xinyuan Tong
|
e3c7f09146
|
Update tool parser and related documentation (#11223)
|
2025-10-07 11:03:40 -07:00 |
|
Chang Su
|
6f1e03a456
|
[router][grpc] Fix sampling_params.stop_strs is None (#11306)
|
2025-10-07 10:57:38 -07:00 |
|
Simo Lin
|
f4affd4df5
|
[router] fix grpc connection conversion and add optimization (#11305)
|
2025-10-07 10:39:33 -07:00 |
|
hzh0425
|
df08bf9b9f
|
[Doc]: Best Practice for HICache (#11001)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: huangtingwei <141888744+huangtingwei9988@users.noreply.github.com>
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
|
2025-10-08 00:59:21 +08:00 |
|
ykwd
|
69efdd27bc
|
[Doc] HiCache Design Documents (#11027)
Co-authored-by: Zhiqiang Xie <xiezhq@stanford.edu>
|
2025-10-08 00:35:45 +08:00 |
|
Chang Su
|
64582caa84
|
[router][grpc] Refactor chat template content format detection (#11288)
|
2025-10-07 08:38:51 -07:00 |
|
Simo Lin
|
2fcd56eaf6
|
[router] add get server info and get model info in grpc server (#11303)
|
2025-10-07 08:36:52 -07:00 |
|
Wenyi Xu
|
0958a39704
|
[Docs] [Router] Update Observability and Common Issues Section (#11302)
|
2025-10-07 08:03:09 -07:00 |
|
Yuan Luo
|
4f42c8cd3e
|
[sgl-kernel] Support float64 moe_sum_reduce cuda kernel (#11068)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
|
2025-10-07 14:31:11 +00:00 |
|
Liangsheng Yin
|
3ddd7dc9f8
|
Introduce future indices (#11301)
|
2025-10-07 22:24:02 +08:00 |
|
Liangsheng Yin
|
501dfa6b42
|
Remove sampling info events and overlap thread file (#11300)
|
2025-10-07 21:34:25 +08:00 |
|
Simo Lin
|
79d3495177
|
[router] add reasoning and tool parser argument in router (#11290)
|
2025-10-07 09:08:32 -04:00 |
|
Liangsheng Yin
|
1519a89cfd
|
Remove overlap thread (#11210)
Co-authored-by: Lianmin Zheng <15100009+merrymercy@users.noreply.github.com>
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
|
2025-10-07 20:12:12 +08:00 |
|
Ke Bao
|
24bc3fb0f9
|
EAGLE cache fix for SWARadixCache (#11231)
Co-authored-by: Hanming Lu <69857889+hanming-lu@users.noreply.github.com>
|
2025-10-07 18:21:37 +08:00 |
|
Liangsheng Yin
|
8a8a608af9
|
[ci] fix pp test (#11294)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
|
2025-10-07 14:20:04 +08:00 |
|
Al-Ekram Elahee Hridoy
|
533e58a15d
|
Feature/longbench v2 evaluation utils (#10949)
|
2025-10-07 14:17:31 +08:00 |
|
Alex Chi Z
|
9b4c449735
|
convert test_deterministic into unit tests (#11095)
Signed-off-by: Alex Chi Z <iskyzh@gmail.com>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2025-10-06 20:33:11 -07:00 |
|
Chang Su
|
a578d300ba
|
[router][grpc] Fix proto3 default value mismatches and cleanup unused fields (#11283)
|
2025-10-06 18:54:51 -07:00 |
|
sglang-bot
|
8c9670375f
|
chore: bump sgl-kernel version to 0.3.15 (#11281)
|
2025-10-06 18:17:51 -07:00 |
|
Yineng Zhang
|
fb27d38305
|
docs: update sgl-kernel README (#11286)
|
2025-10-06 17:55:22 -07:00 |
|
Xinyuan Tong
|
fd8a0b29c0
|
fix: correct scale parameter remapping logic in Llama4ForConditionalGeneration (#11282)
|
2025-10-06 17:28:23 -07:00 |
|
Chenxi Li
|
afc35ccc5e
|
Fix LoRA support for multimodal models (VLMs) by implementing a consistent pattern for skipping vision components (#11261)
|
2025-10-06 17:23:00 -07:00 |
|
sunxxuns
|
a57f0e3d56
|
reverse the amd ci test back to 1200s and split the 8-gpu deepseek job into two. (#11238)
Co-authored-by: root <root@smci350-zts-gtu-e17-15.zts-gtu.dcgpu>
|
2025-10-06 19:27:57 -04:00 |
|
Lianmin Zheng
|
708f4ff490
|
Rename max_micro_batch_size -> pp_max_micro_batch_size (#11279)
|
2025-10-06 15:50:56 -07:00 |
|
Lianmin Zheng
|
e2daeb351c
|
[Auto Sync] Update test_utils.py (20251006) (#11280)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: Sehoon Kim <sehoon@x.ai>
|
2025-10-06 15:49:57 -07:00 |
|
Lianmin Zheng
|
0e7b353009
|
Fix code sync scripts (#11276)
|
2025-10-06 15:35:01 -07:00 |
|
Chang Su
|
b07c9c76c5
|
[router][grpc] Refine streaming processes (#11277)
|
2025-10-06 15:15:01 -07:00 |
|
Lifu Huang
|
748f86f3de
|
[Bug] Fix incorrect assertion in FA4 and add UT. (#11182)
|
2025-10-06 14:58:39 -07:00 |
|
ishandhanani
|
73ea484af1
|
docker: add manifest to versioned docker releases (#11268)
|
2025-10-06 14:53:40 -07:00 |
|
gongwei-130
|
4aeb193fbd
|
disable sm100 for FlashMLA and fast-hadamard-transform in cuda12.6.1 (#11274)
|
2025-10-06 14:48:31 -07:00 |
|
Chang Su
|
466992b2d0
|
[router][tool call] Clean up redundant detect_format and has_tool_markers (#11270)
|
2025-10-06 14:04:02 -07:00 |
|
Zhiyu
|
155cbb51f0
|
Enable native ModelOpt quantization support (1/3) (#7149)
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
|
2025-10-06 13:24:15 -07:00 |
|
Lianmin Zheng
|
eb30b888db
|
Remove env var warnings for release (#11262)
|
2025-10-06 10:09:17 -07:00 |
|
Simo Lin
|
5ee777c98f
|
[router] add ipv6 support across all components (#11219)
|
2025-10-06 08:16:59 -07:00 |
|