Commit Graph
5741 Commits
Author SHA1 Message Date
9db4650e5e [MoE Refactor] Add more MoE layer tests (#39349)
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-04-21 18:12:36 -04:00
bnellnmandGitHub 5e584ce9ec [MoE Refactor] Remove SharedFusedMoE class (#35782)
Signed-off-by: Bill Nell <bnell@redhat.com>
2026-04-21 18:12:12 -04:00
Wentao YeandGitHub 16688b26a6 [Perf] Optimize batch invariant with fused rms norm, 2.1% E2E latency improvement (#40413)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2026-04-21 19:51:03 +00:00
5544f8c18b [Performance] Add is_reasoning_end_streaming() override to GptOssReasoningParser (#35745)
Signed-off-by: Fergus <fergus.barratt00@gmail.com>
Signed-off-by: fergus barratt <fergus.barratt00@gmail.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-04-21 18:31:27 +00:00
Vadim GimpelsonandGitHub 6d85b36a9f Revert #38730 and #38791 (#40032)
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@gmail.com>
Signed-off-by: Vadim Gimpelson <156319763+vadiklyutiy@users.noreply.github.com>
2026-04-21 11:44:11 -04:00
d249a9e90e Add Granite 4.1 Vision as built-in multimodal model (#40282)
Signed-off-by: Artem Spector <artems@il.ibm.com>
Signed-off-by: artemspector <artems@il.ibm.com>
Co-authored-by: artemspector <artems@il.ibm.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-04-21 05:43:39 -07:00
wang.yuqiGitHubCyrus Leungmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
d2e2e856ad [Frontend] Remove frontend pooling multi task support. (#37861)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
2026-04-21 12:27:44 +00:00
766cb65d00 feat(multimodal): support externally processed mm_kwargs with cache injection (#39502)
Signed-off-by: Krish Hung <krishung5@gmail.com>
Signed-off-by: krishung5 <krish@nvidia.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-21 11:31:09 +00:00
Jhao-Ting ChenandGitHub 28c222157b fix: clamp NaN/Inf in topk_softmax to prevent duplicate expert IDs (#39391)
Signed-off-by: Jhao-Ting Chen <jhaotingc@nvidia.com>
2026-04-21 15:04:41 +04:00
Zeyu ZhangandGitHub 5a94a19824 [Bugfix] Normalize malformed dict prompts that carry token IDs in prompt (#40339)
Signed-off-by: Alchuang22-dev <2584829494@qq.com>
2026-04-21 07:44:36 +00:00
0e884fe638 [Bugfix] Fix _CONFIG_REGISTRY types getting wrong config class when on-disk model_type differs (#39554)
Signed-off-by: Misa <misaAle@users.noreply.github.com>
Signed-off-by: Misael Casarez <misacasa@amazon.com>
Co-authored-by: Misael Casarez <misacasa@amazon.com>
2026-04-20 19:04:48 -07:00
fe5c115ee4 [vLLM IR] Add IR op testing and benchmarking infrastructure (#40167)
Signed-off-by: Yanan Cao <gmagogsfm@gmail.com>
Co-authored-by: Theresa Shan <Theresa.Shan@amd.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-21 00:23:03 +00:00
Sage MooreandGitHub 3173441b0f [EPLB] Consolidate is_unchanged/is_received_locally into TransferMetadata (#37341)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
2026-04-20 21:12:42 +00:00
Nicolò LucchesiandGitHub 304d5ba1a0 [Bugfix][CI] Fix tests/distributed/test_torchrun_example_moe.py (#40349)
Signed-off-by: NickLucche <nlucches@redhat.com>
2026-04-20 11:05:44 -07:00
baiandGitHub 191e3fdaa1 Update flashinfer to 0.6.8 (#39959)
Signed-off-by: bai <v@gor.io>
2026-04-20 10:37:23 -07:00
3461c8b027 [EPLB] Refactor Async EPLB synchronization logic (#37601)
Signed-off-by: Sage Moore <sage@neuralmagic.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
2026-04-20 17:05:41 +00:00
726efe177b [MoE Refactor] Move the shared/fused expert output sum into MoERunnerBase (#35949)
Signed-off-by: Bill Nell <bnell@redhat.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
2026-04-20 12:28:46 -04:00
Rita BrugarolasandGitHub fb5635d3f9 [ROCm] Add MLA dual RMS norm fusion (Q, KV) pass for DeepSeek/Kimi-K2 (#39242)
Signed-off-by: Rita Brugarolas Brufau <rita.brugarolasbrufau@amd.com>
2026-04-20 14:56:27 +00:00
Yan MaandGitHub e06de7f005 [XPU] enable triton attention test on XPU by removing cuda device binding (#39627)
Signed-off-by: Yan Ma <yan.ma@intel.com>
2026-04-20 20:57:11 +08:00
zhanqiuhuandGitHub cc3993b05d nixl refactor [2/N]: unify TpKVTopology + HeteroTPTransferConfig into TransferTopology (#39529)
Signed-off-by: Zhanqiu Hu <zhu@redhat.com>
2026-04-20 12:39:08 +02:00
Ilya MarkovandGitHub 50dd4cb427 [EPLB] Add nixl-based eplb communicator (#36276)
Signed-off-by: ilmarkov <markovilya197@gmail.com>
Signed-off-by: Markov Ilya <markovilya19@gmail.com>
2026-04-20 10:24:23 +00:00
f774ba028a [kv_offload+HMA][4/N]: Support sliding window lookup (#36645)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
Co-authored-by: Nicolò Lucchesi <nlucches@redhat.com>
2026-04-20 12:53:51 +03:00
Andreas KaratzasandGitHub a943839e9a [ROCm][CI] Introducing new MI300 nodes (#39531)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2026-04-20 16:09:58 +08:00
wuyingjunandGitHub 77fd2c8631 [Bugfix] Forward mm_processor_kwargs in offline generate APIs (#40251)
Signed-off-by: wuyingjun <wuyingjun_yewu@cmss.chinamobile.com>
2026-04-20 00:56:56 -07:00
Julien DenizeandGitHub 6097afb9bd [BUGFIX] Fix Pixtral consolidated format vision weight loading (#39916)
Signed-off-by: Julien Denize <julien.denize@mistral.ai>
Signed-off-by: juliendenize <julien.denize@mistral.ai>
2026-04-19 22:25:03 -07:00
6e10cb54f6 [Bugfix][Responses API] Fix streaming tool calls on /v1/responses (#39892)
Signed-off-by: Hoang Nguyen <118159510+hnt2601@users.noreply.github.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-04-20 11:24:52 +08:00
daniserebandGitHub d1135a5087 Fix MoE backend selection for LoRA (unquantized MoE) (#40273)
Signed-off-by: Daniel Serebrenik <daserebrenik@nvidia.com>
2026-04-19 17:18:40 +00:00
TJianandGitHub 45232a454e [FEAT] [Perf] [Gemma4] Fused Gemma4 Routing Function Triton (#39083)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2026-04-19 09:57:39 +00:00
Flora FengandGitHub 03ce1c6ed9 [Bugfix] Kimi-K2 tool parser streaming - fix token leakage, argument truncation, and content dropping (#38579)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-19 01:30:27 -07:00
omerpaz95andGitHub 4353c9cb4a [KV Offload] Pass request context (#39185)
Signed-off-by: omerpaz95 <omerpaz95@gmail.com>
2026-04-19 08:54:59 +03:00
Dan AlistarhandGitHub ed0622e3a8 [Attention] TurboQuant: remove redundant random signs, add prior art attribution (#40194)
Signed-off-by: Dan Alistarh <d.alistarh@gmail.com>
2026-04-18 14:31:59 -04:00
Yusuf MohammadandGitHub b5f6c5f834 Added general ND x ND matmul and unit test for it (#39909)
Signed-off-by: Yusuf <yusufmohammad@live.com>
2026-04-18 10:05:21 -04:00
153ba7f0f3 [Refactor] Drop direct dependency on librosa (#39079)
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
2026-04-18 06:55:38 +00:00
80b18230e0 [Frontend] Add multimodal support to /inference/v1/generate endpoint (#38405)
Signed-off-by: Nithin Chalapathi <nithin.ch10@gmail.com>
Signed-off-by: Nithin Chalapathi <nithinc@berkeley.edu>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-04-17 20:31:56 -07:00
milesialGitHubgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
b0755523dc [Core] Reduce mm scheduler, get_num_embed overhead (#40143)
Signed-off-by: milesial <milesial@users.noreply.github.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2026-04-18 11:25:49 +08:00
Michael GoinandGitHub 48a65ccb02 [CI] Speed up test_fused_marlin_moe (#40178)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
2026-04-17 19:26:21 -07:00
Michael GoinandGitHub 1f45e83756 Remove outdated tests test_mixtral_moe and test_duplicated_ignored_sequence_group (#40175)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-17 16:49:43 -07:00
Michael GoinandGitHub a8bffaa133 [Kernel] Add MXFP4 W4A4 CUTLASS MoE kernel for SM100 (#37463)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-17 16:42:32 -07:00
251c18d1f8 skip fp8e4b15 on xpu (#39957)
Signed-off-by: Xinyu Chen <xinyu1.chen@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-04-17 16:55:08 +00:00
sychen52andGitHub 6b2b7bd0eb Add nvfp4 support to reshape_and_cache_flash (#37332)
Signed-off-by: Shiyang Chen <shiychen@nvidia.com>
2026-04-17 07:28:00 -07:00
ChaunceyandGitHub 7a51b3e415 [Bugfix] Fix empty delta detection in Qwen3XMLToolParser streaming (#40090)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
2026-04-17 13:34:55 +00:00
Li, JiangandGitHub d02421a7db [CPU] Refactor CPU affinity and memory management (#39781)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2026-04-17 21:01:08 +08:00
Shinichi HemmiandGitHub 4c47710bf7 [CI/Build] Apply ruff formatter to pass pre-commit (#40078)
Signed-off-by: Hemmi Shinichi <shemmi@preferred.jp>
2026-04-17 08:54:32 +08:00
bnellnmandGitHub 79e799ebbd [Bugfix] Temporarily disable B200 fp4 MoE layer tests (#40057)
Signed-off-by: Bill Nell <bnell@redhat.com>
2026-04-16 19:26:55 -04:00
BadrBasowidandGitHub 29057d3bee [Compilation] Add Unit Tests for VllmFusionPatternMatcherPass (#39692)
Signed-off-by: BadrBasowid <badr.basowid@gmail.com>
2026-04-16 22:57:16 +00:00
Asaf GardinandGitHub ad2b1277f9 [Quantization] Consolidate experts_int8 with fp8 online quantization (#38463)
Signed-off-by: Josephasafg <ajgard7@gmail.com>
2026-04-16 13:12:20 -07:00
roikoren755andGitHub b897f00c9c Gate SSU dispatch setup (#40039)
Signed-off-by: Roi Koren <roik@nvidia.com>
2026-04-16 13:06:01 -07:00
adf9bb3c57 [CI] Add weight transfer tests to CI (#39821)
Signed-off-by: SumanthRH <sumanthrh99@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2026-04-16 15:51:45 -04:00
Roger WangandGitHub 3abb7560c0 [Bugfix] Fix audioflamingo test (#40052)
Signed-off-by: Roger Wang <hey@rogerw.io>
2026-04-16 11:53:58 -07:00
Nikita ShapovalovandGitHub 692db29cd4 [Bugfix] Fix Ray compiled-DAG SHM channel stalls by detaching zero-copy np.ndarray logprobs buffers (#35736)
Signed-off-by: Nikita Shapovalov <nikita@poolside.ai>
2026-04-16 23:49:29 +08:00