|
06cccf8730
|
[Bugfix] Fix int32 token offset overflow in fused SiLU block quant (#53409)
Signed-off-by: Anni <dranox2222@gmail.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
|
2026-08-28 16:23:36 -04:00 |
|
|
|
67e86d1e6f
|
[BugFix] Bind RayExecutorV2 TCPStore before publishing its port (#50969)
Signed-off-by: aoshen02 <aoshen02@users.noreply.github.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen02@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-28 12:27:22 -07:00 |
|
|
afriedriandAndreas Karatzas
|
2f1cba799e
|
[ROCm] remove VLLM_ROCM_USE_AITER_FP4_ASM_GEMM environment variable; make w4a4 use the preshuffle triton+asm by default (#53141)
Signed-off-by: Andy Friedrich <afriedri@amd.com>
Signed-off-by: afriedri <afriedri@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
|
2026-08-28 18:59:53 +00:00 |
|
|
hangy-amd
|
31c579503d
|
update quark docs to include online quantization (#52736)
Signed-off-by: Hang Yang <hangy@amd.com>
|
2026-08-28 18:23:06 +00:00 |
|
|
Yongye ZhuandOpenAI Codex
|
d9dabfa351
|
[Kimi-K3][Kernel] Optimize the low-M fused latent MoE tail (#54168)
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-28 10:45:36 -07:00 |
|
|
Keyi LiandKeyi Li
|
6f91e3d953
|
[Perf] Split xdrope_positions H2D copy into per-row transfers (#53412)
Signed-off-by: Keyi Li <likey6688@gmail.com>
Co-authored-by: Keyi Li <likey6688@gmail.com>
|
2026-08-28 10:28:43 -07:00 |
|
|
Chipmunk
|
ffe690eca9
|
[MM][CG] Support ViT full CUDA graph for Idefics3 and SmolVLM (#47625)
Signed-off-by: Ryouichi Kurihara <ryouichi.kurihara.628@gmail.com>
|
2026-08-28 17:16:31 +00:00 |
|
|
xuebwang-amd
|
06569a8696
|
[ROCm][Quantization][MOE] Enable fused shared experts for block-quantized FP8 (#53097)
Signed-off-by: xuebwang-amd <xuebwang@amd.com>
|
2026-08-28 09:23:07 -07:00 |
|
|
Bugen Zhao
|
11012d2a35
|
[Rust Frontend] Reduce copy in auxiliary frame resolution (#54148)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-08-28 09:01:17 -07:00 |
|
|
Xinyu Chen
|
94a54f581e
|
[XPU]bump up vllm_xpu_kernels to 0.1.14.1 (#54203)
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
|
2026-08-28 07:12:17 -07:00 |
|
|
Michał Ganczarenko
|
d1922cb5a7
|
[Bugfix] Restore multimodal support on the plain "vllm" throughput backend (#52168)
Signed-off-by: Michal Ganczarenko <michal.ganczarenko@intel.com>
|
2026-08-28 10:28:25 +00:00 |
|
|
stefankoncarevic
|
5f213ed159
|
[ROCm][CI] Warm up the RLHF dev server before the pause/resume timing checks (#53594)
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com>
|
2026-08-28 09:07:04 +00:00 |
|
|
Jung Jiyu
|
3bb19cd8a3
|
[Bugfix][CI/Build] Fail closed when selected precompiled CUDA variant is unavailable (#52545)
Signed-off-by: Jung Jiyu <jiyu.jung@navercorp.com>
|
2026-08-28 17:00:48 +08:00 |
|
|
Thien Tran
|
f956e1c343
|
[Kimi-K3][Bugfix] Fix low-latency GEMM fallback initialization (#54167)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-08-28 08:32:20 +00:00 |
|
|
stefankoncarevic
|
9236159bb6
|
[ROCm][CI] Keep startup profiling from aborting when free memory grows (#53591)
Signed-off-by: Stefan Koncarevic <stefan.koncarevic@amd.com>
|
2026-08-28 00:02:40 -07:00 |
|
|
Qiming Zhang
|
c01b50e390
|
[Test] Fix mock_current_vllm_config missing kernel_config in test_dflash2 (#54132)
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
|
2026-08-27 22:28:43 -07:00 |
|
|
maobaolongandCodex
|
6f7df92a8e
|
[CPU][MLA] Fix prefill backend selection so MLA runs end-to-end on CPU (#51471)
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-08-28 12:36:55 +08:00 |
|
|
|
e6bfe03ad7
|
Count store offers, not lookups, for CPU offload store_threshold (#52227)
Signed-off-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Co-authored-by: okorzh-amd <okorzh-amd@users.noreply.github.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
|
2026-08-27 20:21:06 -07:00 |
|
|
haic0andCursor
|
53bf990502
|
[Bugfix][KV Cache] Prevent negative external block allocation (#52707)
Signed-off-by: haic0 <149741444+haic0@users.noreply.github.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
|
2026-08-27 20:10:45 -07:00 |
|
|
Roy WangandClaude Fable 5
|
b74ac0bc61
|
[Bugfix] Allocate packed outputs in fused_q_kv_rmsnorm so q_b_proj keeps its low-latency GEMM path at decode (#53109)
Signed-off-by: yasong.wang <yasong.wang@inferact.ai>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
|
2026-08-28 02:08:27 +00:00 |
|
|
Elvir Crnčević
|
f3b91f1af2
|
Remove wrongly added e2e test (#54099)
|
2026-08-27 20:04:17 -06:00 |
|
|
Nick Hill
|
8cfba696ee
|
[Misc] Separate adaptive verification config validation (#54108)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-27 20:03:01 -06:00 |
|
|
Misha GoinandOpenAI Codex
|
5bbc58c0ad
|
[Bugfix] Remove race in fused groupwise RMSNorm quantization (#54111)
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-27 19:01:22 -07:00 |
|
|
Thien Tran
|
6ec92bcbc8
|
[Kimi-K3] Merge MLA gate into QKV-A projection (#54015)
Signed-off-by: Thien Tran <gau.nernst@yahoo.com.sg>
|
2026-08-27 17:47:18 -07:00 |
|
|
prakharPant
|
b2a6e9dca0
|
fix(build): correct preprocessor guard for GDN decode to fix Ampere c… (#52743)
Signed-off-by: prakharP <prakharpant288@gmail.com>
|
2026-08-27 17:21:44 -07:00 |
|
|
Kevin H. Luu
|
d04d3e0a07
|
[Bugfix] Revert renderer warmup overlap to avoid fork deadlock (#54023)
Signed-off-by: Kevin Luu <51931015+khluu@users.noreply.github.com>
|
2026-08-27 16:36:33 -07:00 |
|
|
Connor CarpenterandBugen Zhao
|
3cc015acd2
|
[Rust Frontend][gRPC] Enforce LoRA path validation across transports (#53756)
Signed-off-by: Connor Carpenter <connorc@nvidia.com>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
|
2026-08-27 16:00:12 -07:00 |
|
|
qizixiandOpenAI Codex
|
e5377e6727
|
[Bugfix][Model] Fix K3 DSpark config for 96-head drafts (#54005)
Signed-off-by: zixi-qi <zixi@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
|
2026-08-27 15:58:28 -07:00 |
|
|
|
7c877062ac
|
[kernel] Integrate FlashInfer BF16 CuTeDSL Low Latency GEMM (#50572)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
|
2026-08-27 22:29:12 +00:00 |
|
|
Fynn Schmitt-Ulms
|
f79a2f5582
|
Add support for loading dflash2 model in speculators format (#53797)
Signed-off-by: Fynn Schmitt-Ulms <fschmitt@redhat.com>
|
2026-08-27 16:12:01 -06:00 |
|
|
Ronaldandaoshen02
|
479eeb32d2
|
[Bugfix][MRV2] Isolate sleep-mode KV allocations (#53508)
Signed-off-by: Ronald1995 <ronaldautomobile@163.com>
Signed-off-by: aoshen02 <aoshen@inferact.ai>
Co-authored-by: aoshen02 <aoshen@inferact.ai>
|
2026-08-27 15:08:28 -07:00 |
|
|
Dennis Yeh
|
d262964e8c
|
Upgrade tpu-inference to v0.28.0 (#54020)
Signed-off-by: dennis yeh <dennis.yeh@cienet.com>
|
2026-08-27 14:25:00 -07:00 |
|
|
Matthew BonanniandOpenAI Codex
|
de9250ac9e
|
[Attention] Enable masked MHA for GLM-5 head dimensions (#53785)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: OpenAI Codex <noreply@openai.com>
|
2026-08-27 21:17:12 +00:00 |
|
|
Mikhail Podvitskii
|
3a9bfc209f
|
[Bugfix][Parser] Scope reasoning-end detection to the current turn via turn-boundary tokens (#54089)
Signed-off-by: Mikhail Podvitskii <podvitskiymichael@gmail.com>
|
2026-08-27 16:57:32 -04:00 |
|
|
Chauncey
|
7d5769b2d9
|
[Perf][DSv4] Use native CUDA SwiGLU clamp kernel for Humming MoE (throughput +1.40%) (#53685)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-08-27 13:52:45 -07:00 |
|
|
Wentao Ye
|
9818bb3db8
|
[Kimi Perf] Tune hopper low latency gemm kernel, 4%~97% performance improvement (#54088)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-08-27 16:48:53 -04:00 |
|
|
Jeffrey Wang
|
79378fe6e8
|
[Bugfix] Avoid TCPStore port collision for co-located non-DP Ray engines (#53666)
Signed-off-by: Jeffrey Wang <jeffreywang@anyscale.com>
|
2026-08-27 19:58:14 +00:00 |
|
|
Bugen ZhaoandNick Hill
|
9db222c6be
|
[Rust Frontend] Align OpenAI request and response edge cases (#53218)
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-08-27 19:23:38 +00:00 |
|
|
Nick Hill
|
4aab2b0ebe
|
[Model Runner V2] Use MRV2 for all models by default (#53183)
Signed-off-by: Nick Hill <nickhill123@gmail.com>
|
2026-08-27 11:59:34 -07:00 |
|
|
Paarth SharmaandWentao Ye
|
a18dbe49ad
|
[Doc] Add EXAONE-4.0-1.2B to batch invariance tested models (#53839)
Signed-off-by: Cogniera <paarths376@gmail.com>
Signed-off-by: Paarth Sharma <paarths376@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
|
2026-08-27 18:38:03 +00:00 |
|
|
Elvir Crnčević
|
674c284dbd
|
Fix Humming MoE activation_output aliasing (#54056)
|
2026-08-27 18:28:38 +00:00 |
|
|
Taneem Ibrahim
|
d7b6a35967
|
[Bugfix] Handle malformed namespace tools (#53763)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-27 14:18:16 -04:00 |
|
|
Summer Yang
|
07242faa46
|
[Attention][DCP] Use FlashInfer native CP for MLA decode (#54012)
Signed-off-by: Summer Yang <girasoleyang@gmail.com>
|
2026-08-27 10:32:45 -07:00 |
|
|
Shanshan Shen
|
32ad1400d7
|
[ROCm][Perf] Fuse SWA q/kv RMSNorm and q FP8 group quant for DeepSeek-V4 (#53540)
Signed-off-by: Shanshan Shen <87969357+shen-shanshan@users.noreply.github.com>
|
2026-08-27 09:37:54 -07:00 |
|
|
Shang Wangandmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
9650dc73e2
|
[CI/Build][Hardware][NVIDIA] Add opt-in Rubin Docker builds (#53443)
Signed-off-by: Shang Wang <samshang.wang@mail.utoronto.ca>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-08-27 16:06:44 +00:00 |
|
|
Chauncey
|
d21c5b50a1
|
[Perf][GLM5.2] Fuse sparse MLA Q concatenation with head padding (#53878)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
|
2026-08-27 11:54:32 -04:00 |
|
|
Nick Hill
|
76c0c6530e
|
[Bugfix][Scheduler] Don't pad spec decode up to max_model_len (#53962)
|
2026-08-27 08:30:22 -07:00 |
|
|
Taneem Ibrahim
|
f18e29834b
|
[Bugfix] Preserve parallel HY-V3 calls delivered in one streaming delta (#53965)
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
|
2026-08-27 11:26:10 -04:00 |
|
|
Matthew Bonanni
|
d85708f7a4
|
[1/N][KV Connector] Identify externally transferable KV cache groups (#53779)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-08-27 11:21:24 -04:00 |
|
|
Khushali Desai
|
c7b0467c25
|
buffer size insuffient Dspark sd for FlashInfer MNNVL allreduce (#50932)
|
2026-08-27 11:01:08 -04:00 |
|