xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2026-04-21 08:27:06 +08:00
Code Issues Packages Projects Releases Wiki Activity
12,227 Commits 155 Branches 89 Tags
Commit Graph

3520 Commits

Author SHA1 Message Date
yuantao
4ad3f75875 Refactor code, add FLASH_ATTN_DIFFKV backend 
Signed-off-by: yuantao <2422264527@qq.com>
 2025-12-22 22:45:11 +08:00
yuantao
a7430ab479 Fix typos 
Signed-off-by: yuantao <2422264527@qq.com>
 2025-12-13 17:59:28 +08:00
yuantao
b565203d92 Refacotr code. Extent FLASH_ATTN to support different KV size and create a new StaticSinkAttention for sink token logics 
Signed-off-by: yuantao <2422264527@qq.com>
 2025-12-13 15:47:33 +08:00
yuantao
de538d3b8f Merge branch 'main' into Add_support_for_openpangu_promoe_v2 
Signed-off-by: yuantao <2422264527@qq.com>
 2025-12-13 10:09:21 +08:00
rasmith
08f8a5627e
[CI/Build][Kernel][BugFix][AMD] Fix per_token_group_quant_fp8 to use correct fp8 min/max values and update atol/rtol in test_quantfp8_group_functionality (#30292) 
Signed-off-by: Randall Smith <ransmith@amd.com>
Co-authored-by: Randall Smith <ransmith@amd.com>
 2025-12-12 18:41:56 -05:00
danielafrimi
13618626df
[MoE-FP8-modelopt] Add FlashInfer alignment padding for intermediate dimensions (#29748) 
Signed-off-by: Daniel Afrimi <dafrimi@pool0-00589.cm.cluster>
Signed-off-by: dafrimi <dafrimi@nvidia.com>
Co-authored-by: Daniel Afrimi <dafrimi@pool0-00589.cm.cluster>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-12-12 20:42:32 +00:00
Xin Yang
1f19d8f899
[Perf] Set split_k to 1 for triton_kernels (#30528) 
Signed-off-by: Xin Yang <xyangx@amazon.com>
 2025-12-12 14:07:57 -05:00
shivampr
cd7740ac5c
[ROCm] Enable Triton ScaledMM fallback + kernel selection fix (#26668) 
Signed-off-by: Shivam <shivampr.dev@gmail.com>
Signed-off-by: Shivam <shivamprasad91@gmail.com>
 2025-12-12 13:28:20 -05:00
Christina Norman
dc13c99eed
fix(gguf): Disable bfloat16 for GGUF on blackwell device (#30408) 
Signed-off-by: Christina <truffle@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Christina Norman <christina@example.com>
Co-authored-by: Isotr0py <isotr0py@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-12 23:10:12 +08:00
Lucas Wilkinson
3e41992fec
[Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-12 05:57:47 -08:00
Jaehwang Jung
f90319d5d1
[Bugfix] Schedule failure due to wrong get_image_size_with_most_features (#29692) 2025-12-12 02:27:20 -08:00
Michael Goin
9f2fc16a69
[Bugfix][Model] Fix Afmoe rope_parameters issue (#30505) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-12 02:53:57 +00:00
Bhanu Prakash Voutharoja
6a6fc41c79
gptq marlin quantization support for fused moe with lora (#30254) 
Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
 2025-12-12 02:27:22 +00:00
jiahanc
0ab23c2b2b
[fix] fix SM check for Flashinfer TRTLLM MOE (#30314) 
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
 2025-12-12 01:00:58 +00:00
Andrew Briand
a00d88973d
[EPLB] Support EPLB w/ NVFP4 (#29804) 
Signed-off-by: Andrew Briand <abriand@nvidia.com>
Co-authored-by: Andrew Briand <abriand@nvidia.com>
 2025-12-11 22:59:40 +00:00
Wentao Ye
c817b14151
[Perf] Optimize deepgemm experts initialization, 3.9% TTFT improvement (#30494) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: li-jinpeng <3332126450@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
 2025-12-11 17:28:34 -05:00
Nicolò Lucchesi
0efd9f867c
[Core] Whisper Enable Encoder Batching (#29421) 
Signed-off-by: NickLucche <nlucches@redhat.com>
 2025-12-11 21:06:51 +00:00
Harry Mellor
cf3eacfe58
Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim (#30389) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-11 20:45:23 +00:00
汪志鹏
0e71eaa644
[Feature] AWQ marlin quantization support for fused moe with lora (#30442) 
Signed-off-by: princepride <wangzhipeng628@gmail.com>
 2025-12-11 18:03:32 +00:00
Harry Mellor
8781cd6b88
Add Eagle and Eagle3 support to Transformers modeling backend (#30340) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-11 17:02:10 +00:00
Harry Mellor
93db3256a4
Give pooling examples better names (#30488) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2025-12-11 16:22:58 +00:00
Cyrus Leung
3a3b06ee70
[Misc] Improve error message for is_multimodal (#30483) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-11 06:39:51 -08:00
Cyrus Leung
13d63b65e0
[Deprecation] Remove missed fallback for embed_input_ids (#30469) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-11 10:06:36 +00:00
Cyrus Leung
979f50efd0
[Deprecation] Remove fallbacks for embed_input_ids and embed_multimodal (#30458) 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
 2025-12-11 06:58:23 +00:00
gh-wf
36c9ce2554
Ensure minimum frames for GLM 4.6V compatibility (#30285) 
Signed-off-by: Wayne Ferguson <wayneferguson@gmail.com>
 2025-12-11 05:26:49 +00:00
Divakar Verma
d1e1fb4363
[Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439) 
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
 2025-12-10 19:47:18 -08:00
Anker
e8e8cd73e5
[Bugfix] Fix HunyuanOCR cross-image contamination in batch processing (#30344) 
Signed-off-by: Lennart Brog <lennart.borg@list-ag.de>
Signed-off-by: Anker <20343812+anker-c2@users.noreply.github.com>
 2025-12-10 18:09:31 +00:00
Lucas Wilkinson
aacf0abf8b
[BugFix] Fix AttributeError: 'MergedColumnParallelLinear' object has no attribute 'weight_scale' (#30399) 
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
 2025-12-10 07:59:23 -08:00
Roger Young
d017bceb08
[BugFix] Fix minimax m2 model rotary_dim (#30384) 
Signed-off-by: xuebi <xuebi@minimaxi.com>
Co-authored-by: xuebi <xuebi@minimaxi.com>
 2025-12-10 04:58:50 -08:00
Wilson Wu
3bdd426636
Fix typos in comments across multiple files (#30345) 
Signed-off-by: Wilson Wu <iwilsonwu@gmail.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-12-09 20:05:28 -08:00
haoyangli-amd
06462392e4
[bugfix][quantization] fix quark qwen3 kv_cache quantization (#30308) 
Signed-off-by: Haoyang Li <lihaoyang0109@gmail.com>
 2025-12-10 03:24:12 +00:00
ElizaWszola
2e7035dd8c
[Bugfix] Fix fp8 DeepGemm compilation issues (#30336) 2025-12-09 20:17:25 -05:00
Charlie Fu
3c680f4a17
[Rocm][torch.compile] Adding layernorm + fp8 block quant and silu + fp8 block quant for Aiter (#25693) 
Signed-off-by: charlifu <charlifu@amd.com>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Charlie Fu <Charlie.Fu@amd.com>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: wuhuikx <hattie.wu@amd.com>
Co-authored-by: Luka Govedič <ProExpertProg@users.noreply.github.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
 2025-12-09 22:39:26 +00:00
Kyle Sayers
fccd532587
[Quantization] FP8 Weight Reloading for Quantized RL Rollout (#28480) 
Signed-off-by: Kyle Sayers <kylesayrs@gmail.com>
 2025-12-09 13:54:32 -08:00
bnellnm
00e5cbb967
[MoE][Refactor] Remove most arguments to FusedMoEMethodBase.apply (#29066) 
Signed-off-by: Bill Nell <bnell@redhat.com>
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Robert Shaw <114415538+robertgshaw2-redhat@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
Co-authored-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
 2025-12-09 13:48:25 -08:00
Tsukasa OI
73a484caa1
[Model][Quantization] Fix / Add GGUF support for Qwen2 MoE models (#30307) 
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
 2025-12-09 19:13:10 +00:00
quanliu
5dcd593baf
[Feature] Batch-Invariant Support for FA2 and LoRA (#30018) 
Signed-off-by: quanliu <18646313696@163.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>
 2025-12-09 10:01:38 -05:00
vllmellm
ee14644ba9
[ROCm] Aiter Quant Kernels (#25552) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2025-12-09 14:27:37 +00:00
Dongjie Zou
1166c31cc7
[Bugfix]: Fix glm46 awq marlin moe wna16 compatibility (#30210) 
Signed-off-by: baonudesifeizhai <baonudesifeizhai@gmail.com>
 2025-12-09 12:20:21 +00:00
wang.yuqi
9c32df6101
[Bugfix] Qwen 3 VL Embedding loading (#30303) 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
Signed-off-by: wang.yuqi <noooop@126.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-09 08:04:02 +00:00
Tsukasa OI
58d5b3f514
[Model][Quantization] Restore MoE + GGUF models support (incl. Qwen3 MoE) by allowing Sideload Parameters (#30116) 
Signed-off-by: Tsukasa OI <floss_llm@irq.a4lg.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
 2025-12-09 05:30:05 +00:00
liangel-02
4b03b50211
update torchao safetensors impl (#30155) 
Signed-off-by: Angel Li <liangel@meta.com>
 2025-12-09 12:46:35 +08:00
Michael Goin
03b91f7262
[Bugfix] Fix compressed-tensors models failing to load with transformers backend (#30287) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
 2025-12-08 20:44:28 -08:00
czhu-cohere
f6227c22ab
[Kernel]Support W4A8 Grouped GEMM on Hopper (#29691) 
Signed-off-by: czhu-cohere <conway.zhu@cohere.com>
 2025-12-08 19:29:06 -08:00
Zhewen Li
ae339b1a67
[Bugfix] Fix DeepGEMM after #29546 (#30267) 
Signed-off-by: zhewenli <zhewenli@meta.com>
Signed-off-by: Zhewen Li <zhewenli@meta.com>
 2025-12-09 01:05:27 +00:00
Wentao Ye
d9417096d1
[Feature] Batch invariant: Enable TRITON_MLA without prefix-caching (#29125) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2025-12-08 19:31:57 -05:00
Ming Yang
9d6235ca9a
[moe] Allow disabling DP chunking (#29936) 
Signed-off-by: Ming Yang <minos.future@gmail.com>
 2025-12-09 00:29:36 +00:00
roikoren755
ae0f69b16a
Add SpecDec support to selective_state_update (#29488) 
Signed-off-by: Roi Koren <roik@nvidia.com>
 2025-12-08 16:45:18 -05:00
Vasiliy Kuznetsov
0d402d2600
online fp8 quant with streaming weight post-processing (#29196) 
Signed-off-by: vasiliy <vasiliy@fb.com>
 2025-12-08 20:15:10 +00:00
shaharmor98
fcd5306f65
Add latent MoE support (#30203) 
Signed-off-by: Shahar Mor <smor@nvidia.com>
Co-authored-by: Tyler Michael Smith <tyler@neuralmagic.com>
 2025-12-08 17:35:01 +00:00