iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
14,386 Commits 3 Branches 0 Tags
fa6a6be51978bd4b49ba0da17039e60f96dc5b13
Commit Graph
4236 Commits
Author SHA1 Message Date
Stan Wozniak daec9dea6e [Bugfix] Correct behavior of GraniteMoeHybrid for TensorParallel execution (#20137) 
Signed-off-by: Stanislaw Wozniak <stw@zurich.ibm.com>
 2025-06-28 08:16:41 -07:00
Nicolò Lucchesi daceac57c7 [Frontend] Generalize v1/audio/transcriptions endpoint (#20179) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-06-28 08:15:26 -07:00
bnellnm c6c983053d [Bugfix] Mark 'hidden_states' as mutable in moe_forward registration. (#20152) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-27 09:42:22 -06:00
Luka Govedič aafabaa0d5 [Fix][torch.compile] Enable custom ops by default when Inductor off (#20102) 
Signed-off-by: luka <luka@neuralmagic.com>
 2025-06-27 09:00:42 -06:00
Robert ShawandRoger Wang d1c956dc0f Gemma3n (Text-only) (#20134) 
Signed-off-by: rshaw@neuralmagic.com <robertgshaw2@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
 2025-06-27 07:16:26 +00:00
wang.yuqi cd4cfee689 [Model][1/N] Automatic conversion of CrossEncoding model (#20012) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-06-26 21:10:04 -07:00
Bowen Wang e9fd658a73 [Feature] Expert Parallelism Load Balancer (EPLB) (#18343) 
Signed-off-by: Bowen Wang <abmfy@icloud.com>
 2025-06-26 15:30:21 -07:00
Wentao Ye c894c5dc1f [Bug Fix] Fix address/port already in use error for deep_ep test (#20094) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-06-26 22:33:13 +08:00
Li, Jiang 0567c8249f [CPU] Fix torch version in x86 CPU backend (#19258) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-06-26 03:34:47 -07:00
lsz05 23a04e0895 [Fix] Support cls pooling in ModernBertPooler (#20067) 
Signed-off-by: shengzhe.li <shengzhe.li@sbintuitions.co.jp>
 2025-06-25 15:07:45 -04:00
Dipika Sikka 02c97d9a92 [Quantization] Add compressed-tensors emulations support for NVFP4 (#19879) 
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
Signed-off-by: Dipika <dipikasikka1@gmail.com>
 2025-06-25 14:28:19 -04:00
cjackal 8359f4c8d8 [V1][Speculative Decoding] Fix DeepSeek MTP (#20022) 
Signed-off-by: cjackal <44624812+cjackal@users.noreply.github.com>
 2025-06-25 08:41:02 -07:00
bnellnm 015fab8c2f [Kernels][Bugfix] Use torch op for all kernels in FusedMoE forward. Add additional testing for cudagraphs. (#19717) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-24 23:22:58 -07:00
Wentao Ye 879f69bed3 [Refactor] Remove duplicate ceil_div (#20023) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-06-25 05:19:09 +00:00
Isotr0py 2273ec322c Revert "Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor" (#20030) 2025-06-25 11:23:29 +08:00
Wentao Ye a6c4b87fbc Revert "[Feature] Integrate new deepgemm (#19820)" (#20049) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-06-24 19:45:22 -07:00
Brayden Zhong 1afa9948f5 [Llama4] Update attn_temperature_tuning (#19997) 
Signed-off-by: Brayden Zhong <b8zhong@uwaterloo.ca>
 2025-06-24 22:42:53 -04:00
Boyuan Feng c01d1c5aba use .dev for version comparison with pytorch nightly release (#20031) 
Signed-off-by: Boyuan Feng <boyuan@meta.com>
 2025-06-24 21:52:16 +00:00
Wentao Ye c6e3bba8e6 [Feature] Integrate new deepgemm (#19820) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-06-24 12:51:56 -07:00
Vadim Gimpelson 9a3b88328f [PERF] Speedup of MRoPE prepare inputs (#19939) 
Signed-off-by: Vadim Gimpelson <vadim.gimpelson@centml.ai>
 2025-06-23 23:01:26 -07:00
Jun-Howie dd2ccf8dde Feat Dynamic Quantization for MoE Layers in GPTQ Marlin Backend (#19395) 2025-06-24 07:23:28 +09:00
Isotr0py 61f4fc5dc6 [Bugfix][v1] Fix step pooler implementation and step pooling usage in v1 (#19956) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-06-23 18:38:06 +00:00
Tyler Michael SmithandVarun Sundar Rabindranath 68aaeb3749 [EP+DP] Optimize the little operations in the DeepGEMM + DeepEP low latency case (#19885) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Signed-off-by: Tyler Michael Smith <tysmith@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-06-23 11:07:47 -07:00
Isotr0py 5111642a6f [Doc] Update V1 status for decoder-only embedding models (#19952) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-06-23 09:31:06 +00:00
Vensen 493c275352 Fix(models/siglip): Add compatibility for Gemma models quantized by llm-compressor (#19643) 
Signed-off-by: Vensenmu <vensenmu@gmail.com>
 2025-06-23 03:40:28 +00:00
Ye (Charlotte) Qi 33d51f599e [BugFix] Add an env to disable moe chunking to work around compile incompatibility (#19642) 
Signed-off-by: Ye (Charlotte) Qi <yeq@meta.com>
 2025-06-22 15:17:49 -07:00
Woosuk KwonandRoger Wang 2c5302fadd [Multimodal] Optimize Qwen2/2.5-VL startup time (#19756) 
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
Signed-off-by: Roger Wang <hey@rogerw.me>
Co-authored-by: Roger Wang <hey@rogerw.me>
 2025-06-21 20:01:07 +00:00
汪志鹏 c3bf9bad11 [New model support]Support Tarsier2 (#19887) 
Signed-off-by: 汪志鹏 <wangzhipeng628@gmail.com>
 2025-06-21 04:01:51 +00:00
Isotr0py 6f170f11dd [Bugfix] Fix bnb 8bit model weights loading (#19917) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-06-21 03:29:09 +00:00
Chendi.Xue 7e8977fcd4 [custom_op][vllm-plugin] update custom_op class to use op_registry (#19164) 
Signed-off-by: Chendi.Xue <chendi.xue@intel.com>
 2025-06-20 07:44:56 -07:00
Adrianandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> f1e840e842 [Model] GPT2ForSequenceClassification model (#19663) 
Signed-off-by: nie3e <adrcwiek@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-06-20 12:07:41 +00:00
qli88 e3a3e4db46 [Bugfix] Enable PP with AITER+V1 (#19822) 
Signed-off-by: Qiang Li <qiang.li2@amd.com>
 2025-06-20 12:43:20 +08:00
Xerxesandxinnan.hou e41bf15cd0 [Chore]: qwen3-moe-type-hints-mistake (#19860) 
Co-authored-by: xinnan.hou <hxn02029096@alibaba-inc.com>
 2025-06-19 21:43:07 -07:00
TJian 2de12be428 [ROCm] [AITER] [Bugfix] Patch for AITER commit 648764942e552a8bb5fe16026703716a81f05374 (#18990) 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2025-06-18 22:56:31 -07:00
Yu-Hang "Maxin" Tang 83ca9ae47b Mark invariant normalizer in Gemma as non-persistent (#19788) 
Signed-off-by: Yu-Hang Tang <Tang.Maxin@gmail.com>
 2025-06-18 22:56:03 -07:00
Lu Fang b1098b4072 [Bugfix] Fix the linter (#19826) 
Signed-off-by: Lu Fang <lufang@fb.com>
 2025-06-18 21:44:41 -07:00
Maximilien de Bayserand22quinn 799397ee4f Support embedding models in V1 (#16188) 
Signed-off-by: Max de Bayser <mbayser@br.ibm.com>
Signed-off-by: Max de Bayser <maxdebayser@gmail.com>
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
Co-authored-by: 22quinn <33176974+22quinn@users.noreply.github.com>
 2025-06-18 21:36:33 -07:00
Jee Jee Li 4959915089 [Quantization] Modify the logic of BNB double quantization (#19742) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-06-19 03:52:09 +00:00
Woosuk Kwon d49adea1f9 [Multimodal] Use fast processor for Qwen2/2.5-VL (#19789) 2025-06-18 15:49:40 -07:00
Russell Bryant 14fdd21d39 [Core] More fixes to MultiModalEmbeddings type handling (#19715) 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-06-18 22:48:29 +00:00
Chen Zhang a89209b78d [v1] Support mamba2 (#19327) 
Signed-off-by: Chen Zhang <zhangch99@outlook.com>
 2025-06-18 20:34:15 +00:00
Wentao Yeandmgoin ffb2cd6b54 [Perf] Optimize moe_align_block_size CUDA kernel (#19572) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-06-17 11:49:26 -07:00
Isotr0py ca94d7fa00 [Bugfix] Update multimodel models mapping to fit new checkpoint after Transformers v4.52 (#19151) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-06-17 15:58:38 +00:00
Di Liu 5b3ad5ecf2 [DOC] fix doc typos (#19600) 
Signed-off-by: Di Liu <liu-di@sjtu.edu.cn>
 2025-06-17 11:34:53 +08:00
Dipika Sikka 6bc7b57315 [Quantization] Remove FP4 emulation; Fall-back to marlin for device < 100 (#19563) 2025-06-16 17:33:51 -04:00
Russell Bryant 90f9c2eb5c [V1] Change return type on get_multimodal_embeddings() (#19446) 
Signed-off-by: Russell Bryant <rbryant@redhat.com>
 2025-06-16 13:32:15 -04:00
qscqesze 387bdf0ab9 [Model] Add support for MiniMaxM1ForCausalLM (shares architecture with MiniMaxText01ForCausalLM) (#19677) 
Signed-off-by: QscQ <qscqesze@gmail.com>
 2025-06-16 09:47:14 -07:00
bnellnm 5e5baa91aa [Kernels] Use empty for modular MoE workspaces (#19667) 
Signed-off-by: Bill Nell <bnell@redhat.com>
 2025-06-16 14:58:01 +00:00
Shawn Tan 4d5424029b [Feature]:Allow for Granite MoE Hybrid models with _only_ shared experts. (#19652) 
Signed-off-by: Shawn Tan <shawntan@ibm.com>
 2025-06-16 11:14:18 +00:00
Szymon Ożóg dec66d253b [Kernel] GGUF MMVQ kernel for multiple input vectors (#18754) 
Signed-off-by: SzymonOzog <szymon.ozog@gmail.com>
 2025-06-16 17:33:26 +08:00