b50fdebce0
[Bugfix] Fix level-2 sleep/wake/reload with enable_lora=True ( #39935 )
...
Signed-off-by: Silen Naihin <silen.naihin@gmail.com >
Co-authored-by: Dakai An <dakaian108@gmail.com >
Co-authored-by: Jiangyun Zhu <riverclouds.zhu@qq.com >
2026-08-06 09:13:10 +08:00
aoshen02 and Andy Lo
8cfa01cdd2
[BugFix] Dense multinode DP rescope with regression test ( #49212 )
...
Signed-off-by: Andy Lo <andy@mistral.ai >
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: Andy Lo <andy@mistral.ai >
2026-08-05 18:12:03 -07:00
gabriel-peracio and Kimi K3
47a4e410ba
[Bugfix][Spec Decode] Fix NaN handling in rejection sampler tl.argmax ( #50183 )
...
Signed-off-by: Gabriel Peracio <gabriel@sigsonic.com >
Co-authored-by: Kimi K3 <noreply@moonshot.ai >
2026-08-05 18:01:09 -07:00
LZW and Roger Wang
d36f24b66a
[KV Connector][Mooncake] Add tenant ID support to MooncakeStoreConnector ( #48069 )
...
Signed-off-by: lzw <2994587066@qq.com >
Co-authored-by: Roger Wang <hey@rogerw.io >
2026-08-05 17:31:18 -07:00
7c77868cdf
[Bugfix] Size and iterate w13 by shard count for non-gated MoE ( #51125 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: Matej Sirovatka <matej.sirovatka@gmail.com >
Co-authored-by: Rishi Puri <riship@nvidia.com >
Co-authored-by: Hsiao-Yuan Chen <littlecircle0730@users.noreply.github.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-08-05 17:24:47 -07:00
Qiu and Lucas Wilkinson
811622c410
[Refactor][PCP] Make PCPManager construction extensible ( #50066 )
...
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com >
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com >
2026-08-05 23:05:14 +00:00
Tianyu Guo
b30291cf0c
[EPD] Remove duplicate image preprocessing in EPD and enable preprocess on GPU ( #50390 )
...
Signed-off-by: Tianyu Guo <guoty@inferact.ai >
2026-08-05 15:59:54 -07:00
Rohan Potdar and Claude Opus 4.8
38ebd97bca
[ROCm] Relax MLA rope+cache test tolerances for bf16 ( #51083 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-08-05 17:50:52 -05:00
Wentao Ye
877975897d
[K3 Perf] Combine multiple all gather together for SP, 1.5~3x kernel level performance improvement ( #51070 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-05 17:42:41 -04:00
bnellnm
373fe8b83e
[MoE Refactor] Remove MoE legacy code ( #51078 )
...
Signed-off-by: Bill Nell <bnell@redhat.com >
2026-08-05 14:35:36 -07:00
Micah Williamson and Andreas Karatzas
4282fe52d5
[ROCm][CI] Add More AITER quantization/MoE kernel tests ( #49375 )
...
Signed-off-by: Micah Williamson <micah.williamson@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-05 21:27:33 +00:00
Netanel Haber
482c613423
[Bugfix][Humming] Preserve ModelOpt FP8 weight dimensions ( #51093 )
...
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com >
2026-08-05 14:08:55 -07:00
Wentao Ye
e76b71f659
[CI Bug] Fix pydantic_core._pydantic_core.ValidationError: Input should be a valid integer ( #51179 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-05 20:57:47 +00:00
stefankoncarevic and Andreas Karatzas
65addac701
[ROCm][CI] Keep rocprofiler-sdk out of DeepEP HT MoE test workers ( #51173 )
...
Signed-off-by: Stefan Koncarevic <Stefan.Koncarevic@amd.com >
Co-authored-by: Andreas Karatzas <akaratza@amd.com >
2026-08-05 15:28:41 -05:00
Rohan Potdar and Claude Opus 4.8
c2d8009044
[ROCm] Work around DeepEP teardown SIGSEGV in MoE test harness ( #51174 )
...
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com >
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com >
2026-08-05 14:44:42 -05:00
Michael Goin
e6d67fddb4
[CI] Prune PyTorch Fullgraph Test ( #51074 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
2026-08-05 12:27:27 -07:00
Michael Goin and OpenAI Codex
8f158d0ee2
[MoE] Share apply_moe_activation support metadata ( #44359 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
2026-08-05 12:05:47 -07:00
14e57ad47d
[Docker][KVConnector] Install mooncake from official wheels instead of a custom build ( #51067 )
...
Signed-off-by: Zhewen Li <zhewenli@inferact.ai >
Co-authored-by: Zhewen Li <zhewenli@inferact.ai >
Co-authored-by: Claude Opus 5 <noreply@anthropic.com >
2026-08-05 11:58:44 -07:00
Wentao Ye
613411a90c
[CI Bug] Fix Chunked prefill is required for mamba cache mode 'align'. ( #51177 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-05 11:33:45 -07:00
fxmarty-amd
bc37fc970e
Revert [Misc] Avoid importing nixl_ep on every vllm serve config ( #50879 ) ( #51176 )
...
Signed-off-by: Felix Marty <Felix.Marty@amd.com >
2026-08-05 11:04:40 -07:00
Wentao Ye
23c0f337b7
[CI bug] Fix Each KV cache group's real block_size must be divisible by has h_block_size ( #51180 )
...
Signed-off-by: yewentao256 <zhyanwentao@126.com >
2026-08-05 14:03:17 -04:00
9833aa53d5
[Bugfix] Fail fast with a clear error when CPU offload region exceeds available space ( #50358 )
...
Signed-off-by: Alex <jihui.huang@daocloud.io >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-05 20:59:55 +03:00
Michael Goin and Shengqi Chen
e8586b2878
[Build] Remove Ubuntu build-stage option from the CUDA dockerfile ( #51060 )
...
Signed-off-by: mgoin <mgoin64@gmail.com >
Co-authored-by: Shengqi Chen <harry-chen@outlook.com >
2026-08-05 10:50:58 -07:00
Ronen Schaffer and Or Ozeri
8543522ca7
[KV Offload] Support out-of-tree secondary tier managers via module_path ( #51007 )
...
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-05 20:30:53 +03:00
zexplorerhj
d4da0c55af
[Model][Frontend] Add Ling 3.0 Flash BF16, MTP, and parser support ( #51045 )
...
Signed-off-by: zexplorerhj <zhjoneson@163.com >
2026-08-06 00:38:28 +08:00
66b3c0e61f
[Kernel][Model] Optimize FA4 mm_prefix range lookup ( #50294 )
...
Signed-off-by: Juqi Li <2223621784@qq.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-05 07:33:49 -07:00
Chauncey and Or Ozeri
62c5e21621
[KV Offloading] Support partial-tail prefix reuse with fine-grained prefix matching ( #50507 )
...
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-05 22:31:50 +08:00
Gabriel Wu and Pavani Majety
08b8613b7b
[Bugfix][Model] Fix MiniMax-M3 NVFP4 inference correctness ( #48929 )
...
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com >
Co-authored-by: Pavani Majety <pmajety@nvidia.com >
2026-08-05 07:25:46 -07:00
cd930c8e78
[Bugfix] Fix MLA kv_b_proj activation dtype with Marlin FP8 ( #38771 )
...
Signed-off-by: Jacob Zhang <jaco8123@gmail.com >
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-05 07:25:41 -07:00
397094da17
Resolve revision to commit_hash once per model load, via huggingface_hub's resolve_revision ( #49990 )
...
Signed-off-by: Wauplin <lucainp@gmail.com >
Signed-off-by: Lucain <lucainp@gmail.com >
Signed-off-by: Lucain Pouget <lucain@huggingface.co >
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com >
2026-08-05 13:49:56 +00:00
music-dino
a9b39d6dcb
[Bugfix] Enable chunked prefill for qwen3.5-0.8B ppl test ( #51153 )
...
Signed-off-by: Dino Music <Dino.Music@amd.com >
2026-08-05 13:21:43 +00:00
Ziming Huang
beca88e59e
[BugFix][K3] Skip moe_intermediate padding when EP is enabled ( #51131 )
2026-08-05 09:22:55 +00:00
Kevin H. Luu and OpenAI Codex
a3b86752fb
[CI] Fix CI authorization notification fallback ( #51095 )
...
Signed-off-by: khluu <khluu000@gmail.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-05 01:34:48 -07:00
Sage and Bugen Zhao
5bf32605a9
[Rust Frontend] Deduplicate request preprocessing for /tokenize ( #50448 )
...
Co-authored-by: Bugen Zhao <i@bugenzhao.com >
Signed-off-by: Sage Ahrac <sagiahrak@gmail.com >
Signed-off-by: Bugen Zhao <i@bugenzhao.com >
2026-08-05 08:27:35 +00:00
fd859d2e06
[KV Connector][Mooncake] Add store group semantics ( #44956 )
...
Signed-off-by: Schatten <czhengt@qq.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: Yifan Qiao <yifanqiao@inferact.ai >
2026-08-05 08:25:38 +00:00
kliuae
f5cd862dbd
[ROCm][Bugfix] Kimi-K3 Fix KDA NaN on mixed batches and racy autotune config ( #50649 )
...
Signed-off-by: kliuae <kuanfu.liu@embeddedllm.com >
2026-08-05 08:07:21 +00:00
MINJUN GIL
b92352ca2c
[Perf][KV Offload] Avoid quadratic ARC batch eviction ( #50992 )
...
Signed-off-by: MINJUN GIL <alswnsrlf12@naver.com >
2026-08-05 10:58:36 +03:00
Kevin H. Luu and OpenAI Codex
96e333e81a
[CI] Run control-plane workflows on vLLM runners ( #51127 )
...
Signed-off-by: khluu <khluu000@gmail.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-05 00:14:27 -07:00
Sundaresan G and Kunshang Ji
999dd8b490
[XPU] Alias is_current_stream_capturing to XPU in cuda wrapper ( #50526 )
...
Signed-off-by: Sundaresan-G <sundaresan.g@intel.com >
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com >
2026-08-05 15:10:17 +08:00
qizixi and Claude Opus 5
4719a9b8f5
[Bugfix][Spec Decode] Fix EAGLE3 DeepSeek draft crash on non-YaRN rope configs ( #51092 )
...
Signed-off-by: zixi-qi <zixi@inferact.ai >
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com >
2026-08-05 14:10:52 +08:00
Tianyu Guo
50c51682a1
[Bugfix][EC Connector] Don't stop an encoder-instance request before its images are encoded ( #50275 )
...
Signed-off-by: Tianyu Guo <guoty@inferact.ai >
2026-08-05 05:53:58 +00:00
Wei-Cheng (Wayne) Chiu and OpenAI Codex
7794b1e08b
[Bugfix] Skip Qwen3 deepstack buffers without vision ( #49397 )
...
Signed-off-by: WEI CHENG CHIU <waynehacking8@gmail.com >
Co-authored-by: OpenAI Codex <noreply@openai.com >
2026-08-05 12:46:23 +08:00
TrainToGPB and Claude
eb3dce9757
[Bugfix][Model] Gemma3n/Gemma4: pad variable-length audio batches ( #50958 )
...
Signed-off-by: TrainToGPB <kaiba0514@gmail.com >
Co-authored-by: Claude <noreply@anthropic.com >
2026-08-05 12:46:00 +08:00
c25093a305
[Kernel] Batch invariant NVFP4 MoE using cutlass ( #40372 )
...
Signed-off-by: Jakub Zakrzewski <jzakrzewski@nvidia.com >
Co-authored-by: OpenAI Codex <codex@openai.com >
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com >
2026-08-05 04:31:32 +00:00
41a7e7da0c
[KV Offload] Support partial secondary-tier load results ( #50321 )
...
Signed-off-by: Moein Khazraee <moein@nvidia.com >
Co-authored-by: Or Ozeri <or@ozery.com >
Co-authored-by: Or Ozeri <oro@il.ibm.com >
2026-08-04 20:48:58 -07:00
aoshen02 and yihengz
6153dbe036
[R3] Unify routed expert shape configuration ( #50940 )
...
Signed-off-by: aoshen02 <aoshen@inferact.ai >
Co-authored-by: yihengz <yihengz@nvidia.com >
2026-08-04 20:20:41 -07:00
Rehan Khan and Li, Jiang <jiang1.li@intel.com>
0187f4c88e
[CPU] Enable tcmalloc for s390x ( #50841 )
...
Signed-off-by: Rehan Khan <Rehan.Khan7@ibm.com >
Co-authored-by: Li, Jiang <jiang1.li@intel.com >
2026-08-05 10:55:39 +08:00
Yejing Lai and mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2cb3ff88cc
[BUGFIX][Quant]Fix test_kv_scale_reload failed ( #50405 )
...
Signed-off-by: Lai, Yejing <yejing.lai@intel.com >
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-08-05 10:50:54 +08:00
Dr Tasos Varoudis and Lucas Wilkinson
c416f15710
[Model] Fix Kimi-K3 MLA with disabled context parallelism ( #50404 )
...
Signed-off-by: Tasos Varoudis <varoudis@archtech.gr >
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com >
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com >
2026-08-05 02:33:14 +00:00
Divakar Verma
bb543efdfd
[ROCm][CI] Add aiter per-token FP8 quant roundtrip and RMSNorm determinism tests ( #50905 )
...
Signed-off-by: Divakar Verma <divakar.verma@amd.com >
2026-08-04 21:32:08 -05:00
