Commit Graph

3513 Commits

Author SHA1 Message Date
Huapeng Zhou
2f7420bc84 [Feat] Enable PDL automatically on Hopper architecture (#5981) 2025-06-01 12:30:17 -07:00
Ravi Theja
c6a0cacc35 Update CI tests for Llama4 models (#6421) 2025-06-01 11:52:15 +08:00
Lifu Huang
0a9bfc20ab [Minor] Always append newline after image token when parsing chat message (#6797) 2025-05-31 20:50:33 -07:00
Yineng Zhang
34c63731fc chore: upgrade sgl-kernel v0.1.5 (#6795) 2025-05-31 18:32:00 -07:00
Lianmin Zheng
2d72fc47cf Improve profiler and integrate profiler in bench_one_batch_server (#6787) 2025-05-31 15:53:55 -07:00
Yineng Zhang
b520d02888 chore: bump sgl-kernel v0.1.5 (#6794) 2025-05-31 14:54:00 -07:00
Qiaolin Yu
7dc0e39442 Bump torch to 2.7.0 (#6788) 2025-05-31 14:43:12 -07:00
Yikai Zhang
fb507b7b10 [FIX] mmmu bench serving result display error (#6525) (#6791) 2025-05-31 13:48:06 -07:00
storyicon
f90945c45a fix(PD-disaggregation): Can not get local ip (#6792)
Signed-off-by: storyicon <storyicon@foxmail.com>
2025-05-31 13:47:14 -07:00
Lifu Huang
094fbdacd5 Fix incorrect LoRA weight loading for fused gate_up_proj (#6734) 2025-05-31 13:41:44 -07:00
YanbingJiang
888cb175a6 Add intel_amx backend for Radix Attention for CPU (#6408)
Co-authored-by: Chunyuan WU <chunyuan.wu@intel.com>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
2025-05-30 21:37:42 -07:00
Chang Su
e39bca0756 ci: relax test_function_call_required (#6786) 2025-05-30 19:18:42 -07:00
Jianan Ji
a2bb856543 Temporarily lower mmlu threshold for triton sliding window backend (#6785) 2025-05-30 18:40:50 -07:00
Cheng Wan
ced3c07afe Support token-level quantization for EP MoE (#6782) 2025-05-30 17:26:30 -07:00
Chang Su
f18b068f15 feat(tool call): Enhance Llama32Detector for improved JSON parsing in non-stream (#6784) 2025-05-30 17:05:17 -07:00
Chao Yang
4fac524b14 update llama4 chat template and pythonic parser (#6679)
Co-authored-by: Chang Su <chang.s.su@oracle.com>
2025-05-30 17:01:22 -07:00
Cheng Wan
b581b22504 Fix one bug in the grouped-gemm triton kernel (#6772) 2025-05-30 01:42:08 -07:00
Li Hui
69dd878b51 Fix shared experts fusion error (#6289) 2025-05-30 01:16:11 -07:00
Jianan Ji
22630ca242 Support sliding window in triton backend (#6509) 2025-05-30 01:11:53 -07:00
Yuhong Guo
d279d4990c Fix aiohttp 'Chunk too big' in bench_serving (#6737) 2025-05-30 00:50:36 -07:00
shangmingc
6cb00c6398 [PD] Optimize time out logic and add env var doc for mooncake (#6761)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-30 00:45:02 -07:00
Xu Wenqing
62cac2c43a Update DeepSeek-R1-0528 function call chat template (#6765)
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
2025-05-30 00:42:57 -07:00
fzyzcjy
2c3b71d678 Improve EPLB logical to physical dispatch map (#6727) 2025-05-29 19:23:54 -07:00
Zilin Zhu
51cdd81f97 [fix][RL] Fix DeepSeekV3ForCausalLM.post_load_weights for multiple update weight (#6265) 2025-05-29 16:28:10 -07:00
Baizhou Zhang
73def253b5 Fix mem_fraction_static for AMD CI (#6748) 2025-05-29 12:37:30 -07:00
JieXin Liang
d9d35def3d [test] add ut and bm for get_last_loc (#6746) 2025-05-29 11:47:21 -07:00
fzyzcjy
6df81e8a39 Support tuning DeepEP configs (#6742) 2025-05-29 08:12:22 -07:00
fzyzcjy
3ab7d9b55e Support picking variants of EPLB algorithms (#6728) 2025-05-29 08:12:01 -07:00
fzyzcjy
7e5071c92a Super tiny enable sole usage of expert distribution metrics and update doc (#6680) 2025-05-29 08:11:38 -07:00
Liangsheng Yin
78689d3393 PD Rust LB (PO2) (#6437)
Co-authored-by: fzyzcjy <5236035+fzyzcjy@users.noreply.github.com>
2025-05-29 20:50:10 +08:00
shangmingc
1dc6864f17 [PD] Support completion endpoint (#6729)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-29 16:26:18 +08:00
ChangyiYang
485a023bd8 refactor apply_w8a8_block_fp8_linear in fp (#6545) 2025-05-29 00:15:11 -07:00
Ke Bao
7e41290082 Add draft extend CUDA graph for Triton backend (#6705) 2025-05-29 00:13:07 -07:00
Chang Su
c673727e0e refactor(tool call): Fix BaseFormatDetector tool_index issue and refactor parse_streaming_increment (#6715) 2025-05-29 00:08:45 -07:00
Xu Wenqing
f4d4f93928 Add DeepSeek-R1-0528 function call chat template (#6725)
Signed-off-by: 许文卿 <xwq391974@alibaba-inc.com>
2025-05-29 00:05:07 -07:00
Baizhou Zhang
f2bd3515fb Tune memory arguments on B200 (#6718) 2025-05-29 00:03:22 -07:00
dongmao zhang
c459536b0f [PD] bug fix: Update status if nixl receiver send a a dummy req. (#6720) 2025-05-29 00:01:56 -07:00
JieXin Liang
535c838674 [fix] more mem for draft_extend cuda_graph (#6726) 2025-05-28 23:25:18 -07:00
JieXin Liang
2163586e63 [feat] triton kernel for get_last_loc (#6676) 2025-05-28 23:10:28 -07:00
iLeGend
e06b076105 Fix PP for Qwen3 MoE (#6709) 2025-05-28 23:06:18 -07:00
Wenxuan Tan
844a8f42c7 Fix LoRA bench (#6719) 2025-05-28 16:38:55 -07:00
Baizhou Zhang
791b3bfabb [Feature] Support Flashinfer fp8 blockwise GEMM kernel on Blackwell (#6479) 2025-05-28 16:03:43 -07:00
fzyzcjy
31589e177e Speed up when having padding tokens two-batch overlap (#6668)
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com>
2025-05-28 16:00:58 -07:00
fzyzcjy
ae6a5b2950 Minor refactor two-batch overlap (#6682) 2025-05-28 15:54:17 -07:00
fzyzcjy
4839999b76 Overlap two kernels in DeepSeek with communication (#6711) 2025-05-28 15:53:51 -07:00
fzyzcjy
541a985f85 Fuse routed_scaling_factor in DeepSeek (#6710) 2025-05-28 15:53:37 -07:00
Hongbo Xu
5170b010a6 [PD] Remove Unnecessary Exception Handling for FastQueue.get() (#6712) 2025-05-28 11:18:24 -07:00
shangmingc
d63e76f735 [CI] Fix setup of disaggregation with different tp (#6706)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-28 11:17:27 -07:00
shangmingc
e9fd11c0d1 [Bugfix] Fix ChatCompletion endpoint of mini_lb when stream is set (#6703)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-28 21:33:36 +08:00
shangmingc
c7588d593e [Bugfix] Fix slice operation when chunk size mismatch (#6697)
Signed-off-by: Shangming Cai <caishangming@linux.alibaba.com>
2025-05-28 21:15:00 +08:00