Commit Graph

4735 Commits

Author SHA1 Message Date
Minglei Zhu
fafaa2ccea [BugFix] fix outplace_fused_experts missing is_gated (#13864) 2025-11-24 12:36:14 -08:00
fzyzcjy
94216a9cc4 Fix quantized moe checker fail for Qwen3 dense fp8 model (#13853) 2025-11-24 11:16:50 -08:00
Yuhao Yao
9535015d05 [Perf] Optimize DeepSeek-R1 w4afp8 glue kernels (#10027)
Co-authored-by: Fan Yin <1106310035@qq.com>
2025-11-24 11:05:38 -08:00
Liangsheng Yin
b60e769d0e Tiny unpin uvloop for other backends (#13858) 2025-11-25 01:34:57 +08:00
Zhi Yiliu
a95a38078b [Fix] Fix uvloop get_event_loop() is not suitable for 0.22.x (#13612)
Signed-off-by: lzy <tomlzy213@gmail.com>
Co-authored-by: lzy <tomlzy213@gmail.com>
2025-11-25 01:20:00 +08:00
YAMY
98b38de3f2 Fix: Safe RoPE Cache Expansion to Prevent Position-ID Out-of-Bounds in EAGLE + Long-Sequence Workloads (#11871) 2025-11-25 01:19:06 +08:00
ant-yy
a146f833f1 [Fix]: Adjust FutureMap's token_id_bufs Size to Prevent ChunkedPrefill's next_token_ids from Overwriting Previous Prefill Requests' next_token_id (#13713)
Signed-off-by: vito.yy <vito.yy@antgroup.com>
2025-11-25 01:08:52 +08:00
StonyPort
1dd9a6ae4d Fix TorchAO quant in VLM (#13508)
Co-authored-by: qiuxuan.lzw <qiuxuan.lzw@alibaba-inc.com>
2025-11-24 22:15:40 +08:00
Yuan Luo
8ef11569a2 [VLM] Revise InternVL Piecewise CUDA Graph Supporting (#13846)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-11-24 22:15:10 +08:00
gaopengff
aeac622058 [Intel XPU]support xgrammar backend for intel xpu (#13245) 2025-11-24 16:48:00 +08:00
Baizhou Zhang
04b52fa8d6 [chore]Upgrade flashinfer to 0.5.3 (#13751) 2025-11-23 23:38:36 -08:00
Yuhao Yang
e5c0f59133 [diffusion] CI: send nightly-test outputs of diffusion to slack for correctness monitoring (#13833)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-11-24 15:22:26 +08:00
Liangsheng Yin
981ca8313f [misc] Rename minilb install env & remove files & fix lint (#13831) 2025-11-24 13:50:00 +08:00
Mick
414248e0d0 [diffusion] doc: minor update contributing.md with test section (#13792)
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-11-24 13:00:08 +08:00
Yuan Luo
f56b9b42e6 [Bugfix] Add jit kernel files in packaging (#13829)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
Co-authored-by: Xu Yongfei <xuyongfei.xyf@antgroup.com>
2025-11-24 12:32:16 +08:00
Liangsheng Yin
b2f7b08c49 Refactor cache init logic (#13800) 2025-11-24 11:41:46 +08:00
Xiaoyu Zhang
9ea1953331 [Doc] Refine fused_moe_triton configs doc (#13820) 2025-11-23 19:09:41 -08:00
liuhuijiayou
dbf22152d6 Fix bug: Incorrect variable used in rem_total_token_offset calculatio… (#13201) 2025-11-24 11:04:34 +08:00
Swipe4057
d5e0346847 xgrammar up version to 0.1.27 (#13650) 2025-11-24 10:53:45 +08:00
Baizhou Zhang
4683e244fe [1/2] Refactor DeepGeem requant for FP8 Linear on Blackwell (#13601)
Co-authored-by: fy1214
2025-11-23 16:07:56 -08:00
yinghui
18403f6bfe make trtllm attn backend's init_forward_metadat non blocking (#13802) 2025-11-23 13:35:40 -08:00
Qiaolin Yu
2892265d4c Tune fp8_w8a8 fused triton moe for GLM-4.6-FP8 (#13815) 2025-11-23 13:29:54 -08:00
hlu1
618ca23802 [Deepseek] Refactor deepseek server_args _handle_model_specific_adjustments (#13687) 2025-11-23 12:41:14 -08:00
Liangsheng Yin
5c2915494c [Scheduler] Tiny organize code style (#13806) 2025-11-23 23:41:34 +08:00
Mick
dd70cf99c1 [diffusion] CI: add run_suite to multimodal_gen CI (#13791) 2025-11-23 21:27:33 +08:00
Mick
d4593964fe [diffusion] feat: support sp for image models (#13180) 2025-11-23 18:11:42 +08:00
Xiaoyu Zhang
b964ce61d6 [DeepEP] Add SGLANG_DEEPEP_BF16_DISPATCH env var in Normal mode (#13787) 2025-11-23 17:32:43 +08:00
DarkSharpness
ac5505b04c [Feature] HiCache JIT kernel (once again) (#13764) 2025-11-22 22:19:16 -08:00
ErsongWang
047935080d Revert "Fix RMSNorm API CALL mismatch issue. (#10032)" (#13727) 2025-11-22 14:25:52 -08:00
cctry
cad7878964 Gather static input buffers for cuda graph (#13676) 2025-11-22 13:01:50 -08:00
Binyao Jiang
b29769f3b6 Move unnecessary input_addr capture under debug mode flag for speed-up (#13690) 2025-11-22 11:42:26 -08:00
Ho-Ren (Jack) Chuang
3990b84bd3 Refactor MHA & MLA KV caches to support FP4 (#13547)
Signed-off-by: Ho-Ren (Jack) Chuang <horenchuang@bytedance.com>
2025-11-22 11:13:43 -08:00
yinghui
5a4394a342 align code style eagle draft&draft_extend cuda graph runner (#13533) 2025-11-23 01:55:16 +08:00
Yuhao Yang
dd303614e0 [diffusion] CI: tinyfix diffusion ci (#13769)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-11-23 01:03:36 +08:00
Liangsheng Yin
863124684c [Spec v2] Remove allocate_lens and enable over-allocation (#13478) 2025-11-22 22:49:10 +08:00
Yuan Luo
5625e32cae [VLM] Replace torch.repeat_interleave with faster np.repeat for Qwen-VL series (#13736)
Co-authored-by: luoyuan.luo <luoyuan.luo@antgroup.com>
2025-11-22 22:45:32 +08:00
Mick
ca548d8324 [diffusion] refactor: refactor sampling params (#13706) 2025-11-22 22:43:04 +08:00
Liangsheng Yin
3397bcee84 Tiny support different prompts in send_one.py (#13768) 2025-11-22 21:59:58 +08:00
Liangsheng Yin
3e804bb0ba Update mem checker during busy (#13704) 2025-11-22 21:15:02 +08:00
Yuhao Yang
a22de641ef [diffusion] fix: fix hunyuanvideo and add 2-gpu ci test (#13720)
Co-authored-by: Mick <mickjagger19@icloud.com>
2025-11-22 20:54:51 +08:00
Liangsheng Yin
ac43822634 Refactor eagle bigram key matching (#13714) 2025-11-22 20:40:42 +08:00
Yijie Zhu
a92afb00c6 [Ascend] support Kimi-K2-Thinking (#12759)
Co-authored-by: ZhengdQin <zhengdqin@gmail.com>
Co-authored-by: richhuan <huan_rz@qq.com>
Co-authored-by: ZhengdQin <46387172+ZhengdQin@users.noreply.github.com>
2025-11-22 17:33:07 +08:00
Trevor Morris
0eea17e3b5 Use dual stream for DS MoE whenever cuda graph is used (instead of with token threshold) (#9405) 2025-11-22 00:37:41 -08:00
Netanel Haber
3805243245 modularize gsm8k and mmmu test classes (#13506) 2025-11-22 16:06:53 +08:00
Baizhou Zhang
8bfce9b08d [Tiny] Renaming environ for NVFP4 dispatch (#13756) 2025-11-22 00:05:20 -08:00
Lianmin Zheng
b41afa3754 [Auto Sync] Update evict_policy.py, radix_cache.py (20251120) (#13669)
Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>
Co-authored-by: cctry <shiyang@x.ai>
2025-11-21 22:07:36 -08:00
alisonshao
94ae816f29 Fix model weights validation with automatic cache cleanup (#13729) 2025-11-22 11:40:00 +08:00
Kangyan-Zhou
59b4d7f8d6 Fix B200 Nightly tests and move one manual test back to unit test to prevent the same issue (#13746) 2025-11-21 17:41:12 -08:00
Shu Wang
a56f770277 Fix global scaling factor loading hang (#13484) 2025-11-21 16:07:06 -08:00
roikoren755
1b48e1b974 Feat/nemotron nano v3 support (#12690) 2025-11-21 13:53:05 -08:00