 Wang, FangYuan
|
9a6f8e5992
|
[AMD] Fix DeepSeek V4 MTP accuracy issue (#30333)
|
2026-07-06 23:57:57 -07:00 |
|
|
|
669fd4b8a5
|
[PP] Fix start_layer_id with pp in get kv_buffer_shape (#29887)
Co-authored-by: ybyang <10629930+whybeyoung@users.noreply.github.com>
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-07-07 14:54:38 +08:00 |
|
|
|
fefc1743a9
|
Cute-DSL FP8 MQA logits (#25220)
Co-authored-by: Mindy Li <11663212+limin2021@users.noreply.github.com>
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-07-06 23:34:07 -07:00 |
|
|
Xiaoyu ZhangandClaude Opus 4.8
|
1da7d3a50b
|
[MoE] Retire the AOT moe_fused_gate / kimi_k2_moe_fused_gate gate kernels (#26771) (#29997)
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
|
2026-07-07 13:53:17 +08:00 |
|
|
DarkSharpness
|
be70bfbdbb
|
[DSA] Fold page-table into fused top-k v2 (decode): drop page_size=1 expansion (#30274)
|
2026-07-06 21:28:05 -07:00 |
|
|
|
36b449af19
|
[EPD] Optimize multimodal global cache with paged embedding pool (#28441)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
Co-authored-by: liusy58 <liusy58@linux.alibaba.com>
|
2026-07-07 12:05:52 +08:00 |
|
|
Zyann
|
541f9221da
|
feat(metrics): add Prometheus metrics for the EPD encoder server (#27564)
|
2026-07-07 12:04:51 +08:00 |
|
|
|
16372b4c5f
|
[Spec] Anchor GLM-5.2 MTP IndexShare topk on the draft-extend step (#29787)
Co-authored-by: kpham-sgl <264503018+kpham-sgl@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <115166877+JustinTong0323@users.noreply.github.com>
Co-authored-by: Xinyuan Tong <xinyuantong.cs@gmail.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-06 20:36:48 -07:00 |
|
|
Siming Dengandsiming-deng
|
df06e03662
|
[MLX] Size the attention KV pool at the compute dtype for quantized models (#30097)
Co-authored-by: siming-deng <deng_siming@apple.com>
|
2026-07-06 20:31:59 -07:00 |
|
|
NOOB
|
c3da0a2582
|
[MLX] Fix single-token chunked-prefill continuation misrouted as decode (#30181)
|
2026-07-06 20:31:33 -07:00 |
|
|
|
3a679459e5
|
[bench] Add agentic-trace multi-turn dataset to bench_serving (#29215)
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-07-06 19:45:44 -07:00 |
|
|
|
e85ef54877
|
Support Cutedsl BF16 GEMM JIT kernel (#30117)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-07-06 19:16:16 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
267ff1b5f9
|
Fix LTX2 RoPE JIT kernel CI (#30278)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-07-07 10:15:21 +08:00 |
|
|
laixinandPeng Zhang
|
6279805962
|
[DSv4] Loading Time Weight Dequant (#27867)
Co-authored-by: Peng Zhang <aniz1905@gmail.com>
|
2026-07-07 09:54:34 +08:00 |
|
|
Yuwei An
|
3cbb7568bd
|
[Experimental] Full Cuda Graph Support for Prefill (#27988)
|
2026-07-06 18:13:03 -07:00 |
|
|
Cheng Wan
|
c861896721
|
[refactor] Resolve config declarations onto server_args at the end of __post_init__ (#30297)
|
2026-07-06 18:04:44 -07:00 |
|
|
Rahul VijayaraghavanandMa Mingfei
|
4b5c612257
|
Skip redundant moe_sum_reduce for single-expert routing on XPU (#22660)
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-07 09:03:16 +08:00 |
|
|
Rockdu
|
7047afafec
|
[diffusion] fix: slice img_shapes per-sample in rollout response extractor (#29989)
|
2026-07-07 08:56:52 +08:00 |
|
|
Ma Mingfei
|
30fb0dd851
|
[CPU] add fused_qk_gemma_norm and refactor norm kernel implementation (#30216)
|
2026-07-07 08:52:59 +08:00 |
|
|
Mick
|
6c1fb8a937
|
[diffusion] fix: fix ragged-caption dynamic-batching accuracy bug in ernie-Image (#30241)
|
2026-07-07 08:41:51 +08:00 |
|
|
nvjullin
|
b41552334d
|
Fix disagg speculative decoding with NIXL connector (#30222)
|
2026-07-06 15:51:33 -07:00 |
|
|
Elizaveta MartirosianandElizaveta Martirosian
|
1c23954cb9
|
[NPU] Add new diffusion tests (#29331)
Co-authored-by: Elizaveta Martirosian <elizaveta.martirosian@gmail.com>
|
2026-07-07 00:40:26 +03:00 |
|
|
Aditya Kamat
|
093256aa4b
|
[Mamba] Fix long-prefill accuracy drop in radix prefix-cache state restore (#29368)
|
2026-07-06 13:57:44 -07:00 |
|
|
Thomasandronnie_zheng
|
ca73c77055
|
[Diffusion] cache cross-attn K/V across denoise steps for Helios (#29755)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-06 23:56:37 +03:00 |
|
|
Brayden ZhongandBrayden Zhong
|
d8462f4961
|
Fixes for NVFP4 numerical accuracy for router GEMM output and wrong correction bias cast (#29783)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-07-06 13:53:05 -07:00 |
|
|
Brayden ZhongandBrayden Zhong
|
8f40b5eb3f
|
When attention TP for linear and full attention, use Flashinfer allreduce fusion (#29699)
Co-authored-by: Brayden Zhong <brayden@radixark.ai>
|
2026-07-06 13:01:53 -07:00 |
|
|
sushil Dubey
|
52c6e27e7e
|
[AMD][diffusion] fix: disable layernorm torch.compile decorator in eager mode on ROCm to avoid memory-access fault (#29673)
|
2026-07-06 11:15:57 -07:00 |
|
|
Junlin Wuandronnie_zheng
|
3abdbab9bb
|
✨ [llm][npu][quant] Add W4A8 MXFP quantization support for Qwen3 Dense on Ascend NPU (#23650)
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-06 19:23:26 +03:00 |
|
|
hhhh1252023
|
1b481deade
|
feat: sync npu nightly test improvements from Ascend testcases (#29403)
|
2026-07-06 22:41:15 +08:00 |
|
|
Thomas Wang
|
80decc78ec
|
[AMD][DeepSeek V4] Set SGLANG_OPT_FLASHMLA_SPARSE_PREFILL to false on hip code path (#30237)
|
2026-07-06 01:25:55 -07:00 |
|
|
Chetan Kumar VermaandMa Mingfei
|
b3ab56545b
|
Add Accuracy Benchmark for OCR models (#25364)
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-07-06 16:18:43 +08:00 |
|
|
chengcuipingandMohammad Miadh Angkad
|
e2b55bdbab
|
NUMA: probe numactl binding and fall back when --membind is rejected (#28401)
Co-authored-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-07-06 16:03:59 +08:00 |
|
|
Mick
|
5f98f62a8a
|
[diffusion] perf: tp-shard every text/image encoder across the full DiT replica (any parallelism) (#30086)
|
2026-07-06 14:48:07 +08:00 |
|
|
Jzz1943
|
de00b838c4
|
[diffusion] fix: pass progressive params through image API (#30148)
|
2026-07-06 14:45:45 +08:00 |
|
|
McZyWu
|
6bb2918938
|
Bugfix qwen prefix cache circumstances (#30047)
|
2026-07-06 14:39:30 +08:00 |
|
|
Lianmin Zheng
|
24c42c90be
|
Clean up ServerArgs post-init dispatch (#30186)
|
2026-07-05 23:05:07 -07:00 |
|
|
Baizhou Zhang
|
5eb1b6a7ba
|
Remove retired DSA env paths (#29912)
|
2026-07-05 22:58:02 -07:00 |
|
|
Mohammad Miadh Angkad
|
b1942fc3ea
|
[Model] Support Qwen3.6 ModelOpt mixed NVFP4 (#27906)
|
2026-07-05 21:31:15 -07:00 |
|
|
|
81735ecf80
|
[AMD ]Feat/dsv4 ep tbo prefill (#29362)
Co-authored-by: wunhuang <wunhuang@amd.com>
Co-authored-by: At1a8 <fangyuan@amd.com>
|
2026-07-05 21:18:34 -07:00 |
|
|
DarkSharpnessandClaude
|
c016c6f355
|
[JIT Kernel] DeepSeek-V4 DSA indexer: faster top-k + page-table transform (runtime k <= 2048) (#26788)
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-07-05 20:23:39 -07:00 |
|
|
Lianmin Zheng
|
9d00385b63
|
Cleanup: relocate temp_set_env and consolidate multi-device/CUDA helpers in common.py (#30180)
|
2026-07-05 18:47:26 -07:00 |
|
|
Lianmin Zheng
|
8673e85e6c
|
Remove # fmt: off from environ.py Envs class (#30153)
|
2026-07-05 12:45:24 -07:00 |
|
|
Lianmin Zheng
|
92a1f6e06c
|
[refactor] Reorder ServerArgs sections common-first; inline LLAMA4/MIMO_V2 arch tuples (#30151)
|
2026-07-05 12:17:24 -07:00 |
|
|
Kevin Flansburg
|
48ba79c11e
|
[BugFix] Release HiCache prefetch resources on disagg-prefill bootstrap-queue abort (#30053)
|
2026-07-06 00:06:59 +08:00 |
|
|
Xiaoyu Zhang
|
931b00f1b0
|
[diffusion] Clean up duplicate helper definitions (#30159)
|
2026-07-05 22:05:11 +08:00 |
|
|
|
addffd7489
|
[Diffusion] Diffusion model support log-requests (#23049)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-05 12:01:26 +03:00 |
|
|
|
b070cb2ae0
|
Fix Diffusion GT generation pipelines (#29926)
Co-authored-by: Elizaveta Martirosian <elizaveta.martirosian@gmail.com>
Co-authored-by: ronnie_zheng <zl19940307@163.com>
|
2026-07-05 11:43:50 +03:00 |
|
|
Cheng Wan
|
8fb99bbaf8
|
[refactor] Config resolution pipeline: full-stack review (10-PR series, review only) (#30137)
|
2026-07-05 00:00:07 -07:00 |
|
|
Yuankai ChenandChun Fang
|
ce733f106b
|
[AMD] Fix RMSNorm batch-invariance on ROCm under deterministic inference (#28787)
Co-authored-by: Chun Fang <chun.fang@amd.com>
|
2026-07-04 23:49:06 -07:00 |
|
|
Mick
|
a37bc2456d
|
[diffusion] refactor: consolidate diffusion weight load planning (#30118)
|
2026-07-05 11:59:50 +08:00 |
|