iHore/vLLM
8
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity
8,269 Commits 3 Branches 0 Tags
54de71d0dfbb6340fdbc620f4ebeb4236d165a37
Commit Graph
2262 Commits
Author SHA1 Message Date
Weixiao Huang c1b4eb048a [feat] move WEIGHT_SCALE_SUPPORTED into raise block to accelerate RLHF weight loading (#21164) 
Signed-off-by: huangweixiao <huangweixiao@msh.team>
 2025-08-04 15:43:06 +08:00
Jee Jee Li a7b8788d2c [Misc] Modify the organization of GLM series (#22171) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-03 23:51:20 -07:00
Chenxi YangandChenxi Yang e5949e5ae0 Remove index_put from MM embeddings merging (#22105) 
Co-authored-by: Chenxi Yang <cxyang@meta.com>
 2025-08-03 22:15:14 -07:00
Yuxuan Zhang d3c18c9cb0 fuse fp32 for GLM-4.5 e_score_correction_bias (#22143) 
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
 2025-08-03 09:04:54 -07:00
Li, Jiang b5dfb94fa0 [CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to torch native implementation (#22145) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2025-08-03 05:34:04 -07:00
Isotr0py 3dddbf1f25 [Misc] Add tensor schema test coverage for multimodal models (#21754) 
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-08-03 00:52:14 -07:00
jiahancandmgoin 337eb23bcc [Fix] Fix llama4 modelopt weight loading error (#22107) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-08-03 00:50:34 -07:00
Yan Ma 73e1b9b1d4 [xpu]support moe models on XPU platform (#21643) 
Signed-off-by: yan <yan.ma@intel.com>
Signed-off-by: Yan Ma <yan.ma@intel.com>
 2025-08-02 07:49:08 -07:00
Chih-Chieh Yang b690e34824 [Model] Mamba2 preallocate SSM output tensor to avoid d2d copy overhead (#21075) 
Signed-off-by: Chih-Chieh Yang <7364402+cyang49@users.noreply.github.com>
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
 2025-08-02 01:59:34 -07:00
Yuxuan ZhangandIsotr0py 25373b6c6c for glm-4.1V update (#22000) 
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
 2025-08-02 01:46:57 -07:00
Chih-Chieh Yang c64861d63c [Bugfix] Mamba2 remove bugged initial state condition in chunk scan (#22034) 
Signed-off-by: Chih-Chieh-Yang <7364402+cyang49@users.noreply.github.com>
 2025-08-01 23:55:57 -07:00
vllmellmandtjtanaavllm d3a6f2120b [FEAT][ROCm] Enable running Flash Attention as ViT attn backend for Qwen-VL models on ROCm platform. (#22069) 
Signed-off-by: tjtanaavllm <tunjian.tan@amd.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: tjtanaavllm <tunjian.tan@amd.com>
 2025-08-01 23:53:18 -07:00
Dipika Sikka 9f9c38c392 [Speculators][Speculative Decoding] Add Qwen Eagle3 Support (#21835) 
Signed-off-by: Dipika Sikka <dipikasikka1@gmail.com>
 2025-08-01 19:43:37 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath a65f46be5e [Misc] DeepGemmExperts : Avoid JIT generation in the hot-path (#21955) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-08-01 19:42:03 -07:00
vllmellmandkf ee2eb6ecd8 [Model] Qwen2.5 VL SiLU-and-Mul (#22066) 
Signed-off-by: kf <kuanfu.liu@embeddedllm.com>
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: kf <kuanfu.liu@embeddedllm.com>
 2025-08-01 19:34:37 -07:00
JartX 3654847db5 feat: Add Support GPTQ Quantization MOE on ROCM vllm serve (#21733) 2025-08-01 21:12:19 -04:00
Harry Mellor 38c8bce8b6 Enable headless models for pooling in the Transformers backend (#21767) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-01 10:31:29 -07:00
Varun Sundar RabindranathandVarun Sundar Rabindranath ac45c44d98 [Bugfix] [Performance] DeepEPHighThroughput + DeepSeek : Quant before Dispatch (#21837) 
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
 2025-08-01 10:14:38 -07:00
Isotr0py 3f8e952179 [Bugfix] Fix glm4.1v video inference issue (#22067) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-08-01 09:33:30 -07:00
Dipika Sikka dfbc1f8880 [Speculative Decoding] Add speculators config support (#21345) 2025-08-01 08:25:18 -04:00
Harry Mellor 87c94bc879 Revert "Update sampling_metadata.py (#21937)" (#22088) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-08-01 05:24:46 -07:00
Jee Jee Li 28b18cc741 [Quantization] Enable BNB support for InternS1 (#21953) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-08-01 11:09:54 +00:00
Aviad Rossmann 53d7c39271 Update sampling_metadata.py (#21937) 
Signed-off-by: Aviad Rossmann <aviadr@neureality.ai>
 2025-07-31 23:23:18 -07:00
Kyle Sayers 0f46a780d4 [Model] [Quantization] Support quantization for Gemma3n (#21974) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2025-07-31 22:45:15 -07:00
Cyrus Leung 82de9b9d46 [Misc] Automatically resolve HF processor init kwargs (#22005) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-31 22:44:10 -07:00
Wentao Ye c3e0e9337e [Feature] Add Flashinfer MoE Support for Compressed Tensor NVFP4 (#21639) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-31 15:26:11 -07:00
Benjamin Chislett 2dff2e21d9 [Bugfix] Fix MTP weight loading (#21941) 2025-07-31 16:33:53 -04:00
zhiweizandRoger Wang 9e0726e5bf [Meta] Official Eagle mm support, first enablement on llama4 (#20788) 
Signed-off-by: morgendave <morgendave@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.me>
 2025-07-31 10:35:07 -07:00
Songandoliveryuan 9484641616 [Model] Add step3 vl (#21998) 
Signed-off-by: oliveryuan <yuansong@step.ai>
Co-authored-by: oliveryuan <yuansong@step.ai>
 2025-07-31 23:19:06 +08:00
amirkl94andmgoin 207b750e19 [NVIDIA] Add SM100 Flashinfer MoE per tensor scale fp8 backend (#21458) 
Signed-off-by: Amir Klein <203507526+amirkl94@users.noreply.github.com>
Signed-off-by: mgoin <mgoin64@gmail.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-31 06:00:01 -07:00
wang.yuqi 2836dd73f1 [Model][CI] Let more pooling models support v1 (#21747) 
Signed-off-by: wang.yuqi <noooop@126.com>
 2025-07-31 01:51:15 -07:00
Jee Jee Li 0f7919fca0 [Misc] Expand SUPPORTED_HIDDEN_SIZES for DeepEP low-latency kernels (#21818) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-30 20:41:12 -07:00
Sanchit Gandhiandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> ec02e536df [Bugfix] Relax lang pin for voxtral (#21833) 
Signed-off-by: Sanchit Gandhi <sgandhi3141@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-07-30 20:38:52 -07:00
Cyrus Leung 004203e953 [CI/Build] Fix registry tests (#21934) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-30 09:10:41 -07:00
Yong Hoon Shin ad510309ee Override attention metadata for fast prefill in some KV sharing setups (#21590) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-30 08:54:15 -07:00
Isotr0py 6e599eebe8 [Bugfix] Fix OOM tests in initialization test (#21921) 
Signed-off-by: Isotr0py <2037008807@qq.com>
 2025-07-30 07:35:47 -07:00
Po-Han Huang (NVIDIA) ff08e51940 [NVIDIA] Fix Llama4 Scout FP4 functionality issues (#21499) 
Signed-off-by: Po-Han Huang <pohanh@nvidia.com>
 2025-07-30 07:33:40 -07:00
aladerran d979dd6beb [Feature][EPLB] Add eplb support for Qwen3 (#20815) 
Signed-off-by: aladerran <aladerran@gmail.com>
 2025-07-30 06:27:57 -07:00
Jee Jee Li fc91da5499 [Model] Remove DSV2 unused code (#21903) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-30 00:55:03 -07:00
Cyrus Leung 2ca5f82c2a [Misc] Remove redundant config definitions (#21891) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-07-29 23:54:18 -07:00
Areeb Syed fdde18229e [Bugfix] Fix shape mismatch assertion error when loading Gemma3n model with BitsAndBytes quantization (#21808) 
Signed-off-by: sydarb <areebsyed237@gmail.com>
 2025-07-30 11:35:21 +08:00
Yong Hoon Shin 9266d98048 [BugFix] Fix interleaved sliding window not set for Gemma3n (#21863) 
Signed-off-by: Yong Hoon Shin <yhshin@meta.com>
 2025-07-29 16:34:19 -07:00
Wenhua Cheng ad341c5194 [Bugfix]fix mixed bits and visual language model quantization in AutoRound (#21802) 
Signed-off-by: Wenhua Cheng <wenhua.cheng@intel.com>
 2025-07-29 07:26:31 -07:00
Jee Jee Li 61a6905ab0 [Model] Refactor JambaForCausalLM (#21394) 
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
 2025-07-29 18:25:07 +08:00
Reza BarazeshandHarry Mellor 37efc63b64 [V0 deprecation] Guided decoding (#21347) 
Signed-off-by: Reza Barazesh <rezabarazesh@meta.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-07-29 03:15:30 -07:00
Isotr0py a4528f0cac [Model]: Fused MoE for nomic-embed-text-v2-moe (#18321) 
Signed-off-by: isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-07-29 03:13:27 -07:00
Benji Beck f1e2c095ec Migrate InternVLImageInputs and InternVLVideoInputs to TensorSchema (#21684) 
Signed-off-by: Benji Beck <benjibeck@meta.com>
 2025-07-28 22:09:45 -07:00
Wentao Ye 48b763d6b5 [Refactor] Merge Compressed Tensor FP8 CompressedTensorsW8A8Fp8MoEMethod and CompressedTensorsW8A8Fp8MoECutlassMethod (#21775) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-07-28 19:47:21 -06:00
Nikhil Guptaandmgoin 89ac266b26 [Feat]: Add support for Dynamic Quant 4 bit CPU kleidiai kernels (#17112) 
Signed-off-by: Nikhil Gupta <nikhil.gupta2@arm.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
 2025-07-28 20:55:15 +00:00
rasmith b361f14e39 [AMD][BugFix] Fix omission of wvSplitK kernel for small batch sizes (1-4) due to torch.compile (#21350) 
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
 2025-07-28 15:38:20 -04:00