7fb7b41a3e
[docs] Qwen3.5 cookbook: multi-node, MTP TP overrides, dense mamba flag ( #26695 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-05-29 12:10:14 -07:00
Aditya Sharma and Xiaodong Ye
b2eed9e16d
[Apple Silicon] Add custom Metal RoPE kernel with fused KV cache store ( #22868 )
...
Signed-off-by: Xiaodong Ye <yeahdongcn@gmail.com >
Co-authored-by: Xiaodong Ye <yeahdongcn@gmail.com >
2026-05-29 15:09:33 +08:00
Baizhou Zhang
69362cbc2c
[Doc] Update benchmark instruction for dsv4 ( #26668 )
2026-05-28 23:37:35 -07:00
40f91e6697
[Bugfix] [DSA] [Hisparse] Broadcast TP Rank 0 Topk Indexes to other TPs ( #24654 )
...
Co-authored-by: xz-keg <xuzou_keg@outlook.com >
Co-authored-by: xuzou <xu.zou@aminer.cn >
2026-05-28 21:14:46 -07:00
Yuhao Yang
a8cfae0b30
doc: update step-3.7-flash docker image tag ( #26625 )
2026-05-29 08:40:17 +08:00
3bdea78ad1
model: support Step-3.7-Flash ( #26565 )
...
Co-authored-by: yhyang201 <yhyang201@users.noreply.github.com >
Co-authored-by: luotingdan <luotingdan@stepfun.com >
2026-05-29 08:00:54 +08:00
Jimmy Shong
f838adb7d4
bench_serving: add Zipfian shared-prefix sampling to generated-shared-prefix ( #26378 )
2026-05-28 14:39:46 -07:00
97d129f8c6
# feat(bench): add SPEED-Bench dataset support to bench_serving ( #24149 )
...
Co-authored-by: zijiexia <37504505+zijiexia@users.noreply.github.com >
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai >
2026-05-28 14:37:00 -07:00
Brayden Zhong and b8zhong
50e0b3b77f
Support Flashinfer Cute-DSL MLA attention ( #24737 )
...
Co-authored-by: b8zhong <b8zhong@users.noreply.github.com >
2026-05-28 00:21:32 -07:00
Brayden Zhong
97dd6aad60
Add a little env var for disabling Flashinfer autotune cache ( #26193 )
2026-05-27 23:59:59 -07:00
Shaoting
14c1bb2721
[Feat][LMCache] Support LMCache mp mode ( #24089 )
...
Signed-off-by: Shaoting-Feng <stfeng@uw.edu >
2026-05-28 10:15:09 +08:00
Qiaolin Yu
561e54f803
Update kimi k25 launch command in cookbook ( #26511 )
2026-05-27 16:04:04 -07:00
loading66
a1ebc4917a
[NPU][DOCS]Add faq and feature Compatibilit ( #26464 )
2026-05-27 17:48:47 +08:00
Baizhou Zhang and Claude Opus 4.7
d6032c04b6
[docs] Fix V4 Pro balanced recipe ( #26451 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-26 23:50:26 -07:00
Zaili Wang
47617cc4df
[CPU Doc]Add Xeon CPU info in Qwen3 Cookbook ( #25971 )
2026-05-26 12:14:07 -07:00
zijiexia and Claude Opus 4.7
6afebc278a
[docs] DeepSeek-V4 cookbook: note cu129 image for GB200 Pro DeepEP backend ( #26413 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-26 12:08:48 -07:00
Baizhou Zhang
f0ba651d66
[Doc] Update pip install commands for Cuda12 ( #26344 )
2026-05-25 22:28:27 -07:00
Ziang Li
2b9dd9c8b3
[FlashInfer v0.6.10] [RL] [DSv32] [GLM-5] Add --dsa-topk-backend and integrate FlashInfer and pytorch topk ( #22851 )
2026-05-25 13:08:03 -07:00
Makcum888e and ronnie_zheng
0801cc05ed
[Diffusion][NPU] Disaggregation diffusion stages support for NPU ( #25895 )
...
Co-authored-by: ronnie_zheng <zl19940307@163.com >
2026-05-25 13:51:25 +03:00
Xiaoyu Zhang
533ef41112
[Diffusion] Default NVFP4 backend to FlashInfer TRTLLM ( #25523 )
2026-05-25 18:14:06 +08:00
Zhangheng and 晟海
a4db563c87
[hisparse]: update user guide ( #26249 )
...
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com >
2026-05-25 17:54:55 +08:00
Junlin Wu
aae04b1241
📝 docs(diffusion): add MXFP4 quantization docs ( #25904 )
2026-05-25 10:24:30 +03:00
zijiexia and Claude Opus 4.7
81cd338fcc
[docs] DeepSeek-V4 cookbook: balanced MegaMoE cap, H200 Pro FP4 mem-frac, nsa-* compat, PD-disagg fixes ( #26164 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-23 02:42:41 -07:00
longxin9715
c69844f043
[NPU]Ascend NPU Performance Profiling Guide and Ascend NPU Operator Development Guide ( #26069 )
2026-05-23 10:50:56 +08:00
jiayisunx
6339295556
[XPU] add apache-tvm-ffi dependency ( #26053 )
2026-05-22 16:09:08 +08:00
zijiexia and Claude Opus 4.7
88a37d7405
[docs] DeepSeek-V4 cookbook: split Quantization axis, add H100 SGLang FP8 ( #26057 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-22 00:52:10 -07:00
Alex O. P.
ae7c4226eb
[diffusion] model: support FLUX.2-klein-base ( #25661 )
2026-05-22 11:24:46 +08:00
McZyWu
b2631a9a4d
[NPU] Docs op performance optimize ( #25830 )
2026-05-22 09:20:13 +08:00
zijiexia and Claude Opus 4.7
17dadebd4e
[Docs] DeepSeek-V4: switch H200 FP4 Pro to flashinfer_mxfp4, Flash Balanced too ( #25923 )
...
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com >
2026-05-21 13:51:40 -07:00
Yuhao Yang
81d686d9fa
Default MegaMoE to W4A8 for Max-Throughput recipe ( #26004 )
2026-05-21 11:54:16 -07:00
amote-i
ac83d8a339
docs: delete deprecated args from npu supported features ( #25995 )
2026-05-21 20:20:29 +08:00
loading66
2e0d2d4c18
[NPU][DOCS]Add best practice and benchmark result parameter description ( #25875 )
2026-05-21 19:08:10 +08:00
jianzhao-xu
f66881f03c
[NPU]Ascend NPU Performance Profiling Guide and Ascend NPU Operator Development Guide ( #25384 )
2026-05-21 17:32:25 +08:00
jiayisunx and Ma Mingfei
34479c19bd
[XPU] upgrade triton-xpu version to 3.7.1 ( #25730 )
...
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com >
2026-05-21 10:29:20 +08:00
Xiaoyu Zhang
ccbbae00ea
[codex] Reland Wan2.2 ModelOpt CI checkpoints ( #25857 )
2026-05-20 22:15:25 +08:00
Cheng Wan and Claude Sonnet 4.6
8131641bc6
[Refactor] Rename NSA → DSA: user-facing aliases, file/class/import rename ( #25821 )
...
Co-authored-by: Claude Sonnet 4.6 (1M context) <noreply@anthropic.com >
2026-05-20 00:18:04 -07:00
Faradawn Yang
da6d549ab2
Update GLM-5 H200 FP8 ( #25814 )
...
Signed-off-by: Faradawn Yang <73060648+faradawn@users.noreply.github.com >
2026-05-20 14:44:54 +08:00
Xinyuan Tong and Xinyuan Tong
52eebc82ae
[Docs] MiMo-V2.5 cookbook: B200 benchmarks + multi-layer EAGLE acceptance profile + long-context reference ( #25359 )
...
Co-authored-by: Xinyuan Tong <xinyuan.tong@radixark.ai >
2026-05-19 23:15:21 -07:00
Cheng Wan
a4b51d35ef
Revert "[codex] Update Wan2.2 ModelOpt CI checkpoints" ( #25845 )
2026-05-19 21:45:20 -07:00
Xiaoyu Zhang
80fc524809
[diffusion] quant: update Wan2.2 modelOpt CI checkpoints ( #25483 )
2026-05-20 09:05:39 +08:00
amote-i
de3fc46e3d
[NPU] [DOC] remove Qwen3-235B-A22B 2K+2K 100ms mixed mode benchmark ( #25778 )
2026-05-19 20:48:43 +08:00
Liangsheng Yin
e0273dcd31
pr-test-extra: re-trigger on labeled event ( #25732 )
2026-05-19 05:15:55 -07:00
Arseniy Mironov and Napkin-AI
45a85efc3a
[Diffusion][NPU]Add attention backends for diffusion models for Ascend NPU ( #23482 )
...
Co-authored-by: Napkin-AI <arseniy.mironov.dev@gmail.com >
2026-05-19 12:46:55 +03:00
amote-i
1f7bf155c3
[NPU] [DOCS] Improved the usability of Ascend NPU documents ( #25735 )
2026-05-19 16:22:22 +08:00
Ziang Li
78cb38ed5e
[FlashInfer v0.6.11] [RL] Support FlashInfer per-token NVFP4 MoE ( #22918 )
2026-05-19 01:04:48 -07:00
Kurkur
d028697d17
[NPU][Docs] Add Kimi-K2.5-W4A8 instance doc on NPU ( #25269 )
2026-05-19 09:08:28 +08:00
54eb2904a4
minor: docs include mac installation ( #25178 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Kangyan-Zhou <zky314343421@gmail.com >
2026-05-18 15:48:59 +08:00
Xia Weiwen and Ma Mingfei
8d5ed330cc
[XPU] Enable qwen3.5 on XPU ( #21668 )
...
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com >
2026-05-18 14:59:19 +08:00
a080358cac
[Refactor] Refactor DeepEP dispatcher ( #22822 )
...
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Cheng Wan <54331508+ch-wan@users.noreply.github.com >
2026-05-18 04:36:42 +03:00
Baizhou Zhang
6dcacb1159
[Doc] Fix several places for dpsk v4 cookbook ( #25506 )
2026-05-16 21:54:15 -07:00
