 Aurick Qiao
|
9a9e167179
|
[Bugfix] Fix full prefill CUDA graph padding and EAGLE capture (#35588)
|
2026-08-30 21:30:24 -07:00 |
|
|
YAMY
|
2ea6d17eab
|
fix(staging): make empty staging rings reusable (#37166)
|
2026-08-30 20:59:57 -07:00 |
|
|
YC Yen-Ching TsengandAlex Nails
|
5972211977
|
[AMD] Fix the QuickReduce bf16 cast failing to build for CDNA (#37132)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
|
2026-08-30 20:57:29 -07:00 |
|
|
Mick
|
881cbfe54c
|
[diffusion] feat: add exact component precision overrides (#36991)
|
2026-08-31 11:12:07 +08:00 |
|
|
Pavan Sivaram GirijalaandYanbingJiang
|
4dc7dc8518
|
[Fix] Transformers-fallback (GPT-NeoX) + KV pool config (DeepSeek-VL2) (#35244)
Co-authored-by: YanbingJiang <yanbing.jiang@intel.com>
|
2026-08-31 11:05:50 +08:00 |
|
|
Piotr MazurekandKhoa Pham
|
046454404a
|
[Spec] Add LFM2 and LFM2-MoE DSpark speculative decoding support (#31041)
Co-authored-by: Khoa Pham <khoa.pham@radixark.ai>
|
2026-08-30 20:03:59 -07:00 |
|
|
jambow0320andShangming Cai
|
7700602278
|
[PD] Align defensive protocol behavior across Mooncake, NIXL, and Mori (#35281)
Co-authored-by: Shangming Cai <csmthu@gmail.com>
|
2026-08-31 10:57:56 +08:00 |
|
|
Cui LilyandMa Mingfei
|
3139ceaeec
|
[XPU] Use SYCL kernels for topk_transform on XPU (#33318)
Signed-off-by: Cui, Lily <lily.cui@intel.com>
Co-authored-by: Ma Mingfei <mingfei.ma@intel.com>
|
2026-08-31 10:33:19 +08:00 |
|
|
YanbingJiang
|
a9d5ca723a
|
[CPU] Fix weight missing issue in fused_input_proj_cpu for GPTQ INT4 for Qwen 3.5 (#35805)
|
2026-08-31 10:14:41 +08:00 |
|
|
Mohammad Miadh Angkad
|
4f761e8649
|
[Deps] Bump FlashInfer to 0.6.18 (#36954)
|
2026-08-30 19:02:39 -07:00 |
|
|
Ali Ihsan Nergiz
|
0da6a66856
|
[MLX] Fix startup crash when reporting preloaded weights (#37035)
|
2026-08-30 17:36:13 -07:00 |
|
|
Xiaoyu Zhang
|
bb5e619860
|
[diffusion] perf: absorb Qwen-Image output projection biases (#37116)
|
2026-08-31 08:25:37 +08:00 |
|
|
Liangsheng Yin
|
4bb8de34cc
|
[mem_cache] Share one ReqKvInfo between a streaming session slot and its request (#37108)
|
2026-08-30 16:36:48 -07:00 |
|
|
|
4bea51d885
|
feat(unified-memory): dense KV views for uniform-row MHA/SWA models (#34602)
Co-authored-by: Caihua Li <caihua.li@bytedance.com>
Co-authored-by: Cheng Wan <cheng.wan@radixark.ai>
|
2026-08-30 15:10:12 -07:00 |
|
|
Liangsheng Yin
|
007ef5e23a
|
[mem_cache] Move req_pool_idx into ReqKvInfo (#37094)
|
2026-08-30 14:46:21 -07:00 |
|
|
Yuzhen ZhouandJiajun Li
|
8a87079dbb
|
Fix stale GLM MoE routing after runtime weight updates (#35883)
Co-authored-by: Jiajun Li <jiajun.li@radixark.ai>
|
2026-08-30 14:13:34 -07:00 |
|
|
Xiaoyu Zhang
|
5ab97c4f44
|
[Diffusion] Cache Qwen-Image modulation across serial CFG branches (#37090)
|
2026-08-31 01:40:29 +08:00 |
|
|
Xiaoyu Zhang
|
8c28cdd116
|
[Diffusion][Kernel] Fuse Wan2.2 NVFP4 bias + GELU on Blackwell (#37075)
|
2026-08-31 01:37:35 +08:00 |
|
|
Zhanghengand晟海
|
6a9366f036
|
[Unified Cache Linker][2/N]: Add device pool assembly for external linkers (#37098)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
|
2026-08-30 23:54:00 +08:00 |
|
|
YAMY
|
84e56982b6
|
[Fix] Fix transformer loader fallback test fixture (#37142)
|
2026-08-30 08:28:11 -07:00 |
|
|
Zhanghengand晟海
|
c9eb475a88
|
[Unified Cache][1/N]: Support cache contract for external linker (#37091)
Co-authored-by: 晟海 <huangtingwei.htw@antgroup.com>
|
2026-08-30 22:24:13 +08:00 |
|
|
Mick
|
fe694986a2
|
[diffusion] chore: make malformed component execution options fail-fast (#37049)
|
2026-08-30 21:06:19 +08:00 |
|
|
Mick
|
e6a6492057
|
[vlm] fix: preserve per-request vit graph metadata for qwen-vl (#37043)
|
2026-08-30 21:02:14 +08:00 |
|
|
WenhaoZhang
|
e9a7157615
|
[diffusion] feat: allow cache-dit with dit layerwise offload (#35858)
|
2026-08-30 20:55:41 +08:00 |
|
|
Mick
|
26c754e06e
|
[vlm] fix: recover multimodal decode and processor failures (#36983)
|
2026-08-30 20:50:19 +08:00 |
|
|
Mick
|
aa483ab782
|
[diffusion] feat: support streaming native vae weights directly to gpu (#37004)
|
2026-08-30 20:48:09 +08:00 |
|
|
Cheng WanandClaude Opus 5
|
e51a3ae65e
|
[Config] Round 5.2: the per-model declarations get their own modules (#37087)
Co-authored-by: Claude Opus 5 <noreply@anthropic.com>
|
2026-08-30 02:24:35 -07:00 |
|
|
Cheng Wan
|
7e751153eb
|
[Config] Round 5.1: the published-side readers ask the bags, and a platform fact gets one address (#37086)
|
2026-08-30 02:18:33 -07:00 |
|
|
Mick
|
a6e4021368
|
[diffusion] chore: reject incompatible transformer fallback (#36917)
|
2026-08-30 16:33:14 +08:00 |
|
|
Jason Wiemels
|
e635577431
|
[rotary] Fix the fused Qwen3.5 RoPE kernel discarding mrope height and width (#34446)
|
2026-08-30 15:37:40 +08:00 |
|
|
Oguz Ulgen
|
d249672ad3
|
Scatter mm embeddings with row index_copy_ instead of masked_scatter_ to cut transient GPU memory (#37070)
|
2026-08-30 00:15:39 -07:00 |
|
|
Lin Junrong
|
512df615de
|
[Bugfix] Hold references to fire-and-forget tasks in disaggregation (#33048)
|
2026-08-30 14:26:34 +08:00 |
|
|
Liangsheng Yin
|
5ec959965b
|
[mem_cache] Settle extend kv_committed_len inside alloc_for_extend (#37085)
|
2026-08-29 23:14:31 -07:00 |
|
|
Liangsheng Yin
|
0438b16154
|
[mem_cache] Move kv_committed_len into ReqKvInfo (#37078)
|
2026-08-29 22:42:25 -07:00 |
|
|
EchO
|
5b7c62d5d6
|
fix(frontend): bound stop strings and regex patterns (#37029)
|
2026-08-29 22:25:26 -07:00 |
|
|
Alex Nails
|
78fa921189
|
[ROCm] Fix QuickReduce fp16 saturation corrupting bf16 all-reduces (106M non-finite -> 0, +0.3%) (#34484)
|
2026-08-29 22:08:17 -07:00 |
|
|
Baizhou Zhang
|
a7ee399904
|
Bump sgl-deep-gemm to v0.1.6 (#36998)
|
2026-08-29 19:51:02 -07:00 |
|
|
Liangsheng Yin
|
6be767c2d2
|
[mem_cache] Move cache_protected_len and swa_evict_floor into ReqKvInfo (#36982)
|
2026-08-29 19:37:53 -07:00 |
|
|
|
ed39568e79
|
[MoE] Add extension points for custom runner backends (#32665)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-29 19:03:41 -07:00 |
|
|
EchOandGuanyi Chen
|
ca8ff035c3
|
fix(hicache): isolate decode offload state per request (#37026)
Co-authored-by: Guanyi Chen <939416532@qq.com>
|
2026-08-29 18:15:05 -07:00 |
|
|
karverma-amd
|
fbecd75c83
|
[AMD] fix: do not emit a shared-expert marker twice on the per-rank slot path (#36515)
|
2026-08-29 18:09:33 -07:00 |
|
|
Liangsheng Yin
|
9a489f8d2f
|
[Test] Move gpqa and aime25 onto sgl-eval, drop unused eval paths (#36979)
|
2026-08-29 17:36:13 -07:00 |
|
|
Neeraj KashyapandBaizhou Zhang
|
032fe91bf1
|
Handle unlimited tokenizer context lengths (#37054)
Co-authored-by: Baizhou Zhang <sobereddiezhang@gmail.com>
|
2026-08-29 17:29:11 -07:00 |
|
|
|
f60bc73c58
|
[Spec] Fix Dspark and Dflash state divergence across TP rank (#33614)
Co-authored-by: hnyls2002 <lsyincs@gmail.com>
Co-authored-by: Liangsheng Yin <hnyls2002@gmail.com>
|
2026-08-29 17:27:43 -07:00 |
|
|
|
a1fe4e30a9
|
[Kernel] Fix SM90 FP8 decode regression with benchmarked M/K/N routing (#37018)
Co-authored-by: John Doe <johndoe@example.com>
Co-authored-by: BBuf <1182563586@qq.com>
|
2026-08-29 16:59:30 -07:00 |
|
|
Alex NailsandClaude Opus 5
|
00fbb6e8ac
|
[Perf] Tune the W4AFP8 DeepEP low-latency requant launch geometry (#35760)
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-29 16:03:01 -07:00 |
|
|
|
3a0f1a1344
|
[NPU] fix: reach torch>=2.8 CUDA memory-pool APIs lazily via torch._C (#29100)
Co-authored-by: Alex Nails <alex.nails@radixark.ai>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-29 15:55:14 -07:00 |
|
|
Junlin Wu
|
09ecb9aaaa
|
📝 [NPU] Use vendor-neutral wording in quantization comments (#36768)
|
2026-08-29 23:05:35 +03:00 |
|
|
|
6afb5e1771
|
Gate the idle-loop tree-cache sanity check behind a default-off env (#36205)
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: hzh0425 <hzh0425@apache.org>
|
2026-08-30 00:10:28 +08:00 |
|
|
Mick
|
b24bd44556
|
[diffusion] feat: avoid direct GPU parameter copies (#36832)
|
2026-08-29 22:43:25 +08:00 |
|