karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity
17,642 Commits 354 Branches 175 Tags
e3b4fdaf5db1aed53675c8467bc4862ba53bbfff
Commit Graph
17642 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Alexander MatveevandAlexander Matveev e3b4fdaf5d perf: add push-based allreduce for small tensor reductions 
Port SGLang's push-based 2-buffer allreduce protocol into vLLM as a new
communicator backend for small-message reductions. The push protocol
eliminates the two explicit cross-GPU NVLink barrier round-trips used by
the existing barrier-based CustomAllreduce, replacing them with a
sentinel-based data arrival detection mechanism and double-buffered epoch
alternation.

Key advantages over the barrier-based approach:
- Zero barriers: data arrival IS the synchronization (positive-zero sentinel)
- Single NVLink round-trip instead of two barrier exchanges + remote reads
- All SMs active (SM_count CTAs vs 2 CTAs) for higher NVLink bandwidth
- No cudaMemcpy to IPC staging buffer in eager mode
- PDL (griddepcontrol) support for kernel overlap on sm_90+

The new PushAllReduce is inserted in the CudaCommunicator dispatch chain
above the existing CustomAllreduce for messages below a size threshold
(~720 KB at TP=8). Larger messages continue to use the barrier-based
path. The existing CustomAllreduce code is not modified.

Measured results on DeepSeek-V4-Pro (61 layers, TP=8, 8x NVIDIA B200,
BS=1, decode with ISL=4, OSL=33024):
- Throughput: +2.14% (84.06 vs 82.30 tokens/s)
- TPOT: -2.09% (11.90 vs 12.15 ms/token)

Correctness verified via lm_eval gsm8k 5-shot with no regression
(exact_match delta within statistical noise).

The feature can be disabled at runtime via VLLM_DISABLE_PUSH_ALLREDUCE=1
to fall back to the barrier-based path.

Signed-off-by: Alexander Matveev <amatveev@redhat.com>
 2026-06-15 16:23:12 -04:00
Flora FengandGitHub cd9078fe59 [Frontend] Skip structural tags for auto tool_choice without strict mode (#45600) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
 2026-06-15 19:55:31 +00:00
Wentao YeandGitHub e18fe932ca [Perf] Optimize DSv4 prefill chunk planning, 4.0% E2E Throughput Improvement (#45061) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-06-15 19:50:21 +00:00
yzong-rhGitHubBen Browning
 		51ec5cf08f [Bugfix] Chat Completions Harmony Refactor Clean up (#45464) 
Signed-off-by: Yifan Zong <yzong@redhat.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
 2026-06-15 14:45:19 -04:00
Ronen SchafferGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		7e612a0f06 [KV Offloading] Implement reset_cache for TieringOffloadingManager (#44541) 
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-15 18:42:53 +00:00
+1
youkaichaoGitHubOpenAI CodexIsotr0pyThien TranBugen ZhaoJee Jee LiRoger WangfunctionstackxYongye ZhuJee Jee Li
 		0a1c5034f5 [Model] Add MiniMax M3 support (#45381) 
Signed-off-by: youkaichao <youkaichao@gmail.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Signed-off-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: OpenAI Codex <codex@openai.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Thien Tran <gau.nernst@yahoo.com.sg>
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
 2026-06-16 01:01:25 +08:00
RoyWangandGitHub a3195fab7b [AMD][Bugfix][Quantization] Honor fused-name match in is_layer_skipped (#43981) 2026-06-15 09:37:52 -07:00
Flora FengandGitHub 0d80979644 [Chore] Consolidate reasoning/tool parser attributes into unified Parser in chat serving (#45548) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
 2026-06-15 11:16:45 -04:00
SaddssandGitHub 588db18362 [Bugfix] Two-phase KV allocation for cross-group prefix cache hits (supersedes #33775) (#44409) 
Signed-off-by: Saddss <2872669061@qq.com>
 2026-06-15 22:39:59 +08:00
Mike GGitHubMichael Gschwind
 		fa63bb9db6 Remove redundant Triton KV cache dtype asserts and enforce architectural support (fp8 >= sm89) (#43914) 
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
Co-authored-by: Michael Gschwind <mgschwind@nvidia.com>
 2026-06-15 06:49:57 -07:00
Xin HeGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Kunshang Ji
 		5ed15f42b9 Fix the E8M0 scale computation in the MXFP4 (W4A4) MOE CUTLASS kernel (#43557) 
Signed-off-by: Xin He <xin3.he@intel.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-06-15 06:04:54 -07:00
Juan Pérez de AlgabaandGitHub b997071ec4 (security) Enforce audio upload size limit before full file materialization (#45510) 
Signed-off-by: jperezde <jperezde@redhat.com>
 2026-06-15 10:25:24 +00:00
Martin KuklaandGitHub 6c5872efc5 [Bugfix] Unset HF's default max_new_tokens for DiffusionGemma (#45417) 
Signed-off-by: Martin Kukla <martin.kukla@cantab.net>
 2026-06-15 17:31:57 +08:00
wang.yuqiandGitHub 1d88c4dadd [Docs] Update the online serving docs. (#45676) 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
 2026-06-15 17:23:36 +08:00
vllmellmandGitHub 25c53d1293 [ROCm][Doc] Add installation notes about python version requirement (#45671) 
Signed-off-by: vllmellm <vllm.ellm@embeddedllm.com>
 2026-06-15 17:22:55 +08:00
Yejing LaiandGitHub 9872921c5f [XPU] skip UT test_with_ngram_gpu_spec_decoding (#44423) 
Signed-off-by: Lai, Yejing <yejing.lai@intel.com>
 2026-06-15 08:46:30 +00:00
ReidandGitHub c17e2f7c84 [Bugfix][Rust Frontend] Make metrics respect --served-model-name (#45465) 
Signed-off-by: reidliu41 <reid201711@gmail.com>
 2026-06-15 08:05:10 +00:00
FAUSTandGitHub 40eac9a9d9 [Rust Frontend] Support parallel_tool_calls = false (#44760) 
Signed-off-by: zhoujinyu <2319109590@qq.com>
 2026-06-15 07:50:48 +00:00
Giancarlo DelfinGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		b5adb027ad [Models] Fix MiMo v2.x QKV TP sharding + FP4 support (#45200) 
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-15 15:13:34 +08:00
Sahil SinghandGitHub 64833f8158 [Rust Frontend] Add external→internal request-id map for abort() (#45137) 
Signed-off-by: Sahil Singh <sahiilsiingh37@gmail.com>
 2026-06-15 06:51:24 +00:00
Will EatonGitHubBugen Zhao
 		ddad5dbda2 [Bugfix][Rust] Sync EngineCoreReadyResponse with the Python dataclass (#45557) 
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: Will Eaton <weaton@redhat.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-06-15 06:49:42 +00:00
Peter PanandGitHub ebb0a71ad0 [Bugfix] Reject out-of-range temperature values in SamplingParams (#44965) 
Signed-off-by: Peter Pan <Peter.Pan@daocloud.io>
 2026-06-14 23:12:44 -07:00
Ting SUNandGitHub 48df95c43e [Feature][Frontend] Report multimodal token counts in usage.prompt_tokens_details (#45458) 
Signed-off-by: Ting Sun <suntcrick@gmail.com>
 2026-06-15 05:20:58 +00:00
Tiezhen WANGGitHubClaude
 		7df4fe1bd7 [Model] Remove XverseForCausalLM (#45638) 
Signed-off-by: Xianbao QIAN <xianbao.qian@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-14 22:09:00 -07:00
Roger WangGitHubClaude Opus 4.8Nick Hill
 		b8336c3c7c [Bugfix][V1] Split V2 model-runner attention groups on num_heads_q (#45564) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-06-14 21:49:46 -07:00
Roger WangGitHubClaude Opus 4.8
 		e8d3e22c88 Fix included router missing path for FastAPI >=0.137 (#45629) 
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-15 04:28:52 +00:00
Ben BrowningGitHubFlora Feng
 		c4a3f9d137 [Frontend] Add Streaming Parser Engine and new Qwen3 Parser (#45413) 
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Flora Feng <4florafeng@gmail.com>
 2026-06-15 11:59:05 +08:00
Flora FengandGitHub e3e3cd5458 [Bugfix][CI] Update Dockerfile dependency graph PNG (#45602) 
Signed-off-by: sfeng33 <4florafeng@gmail.com>
v0.23.1rc0 		2026-06-15 10:35:24 +08:00
Li, JiangandGitHub 8760f972ca [CPU] Refine CPU attention frontend (#45391) 
Signed-off-by: jiang1.li <jiang1.li@intel.com>
 2026-06-14 19:26:54 -07:00
maobaolongGitHubLi, Jiang <jiang1.li@intel.com>
 		b675cb7d0f [Bugfix][CPU] Honor cgroup memory limit when computing KV cache size (#45086) 
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Li, Jiang <jiang1.li@intel.com>
 2026-06-14 19:26:50 -07:00
Chaojun ZhangandGitHub 2725c84aae [XPU] Enable sequence parallel support for XPU (#38608) 
Signed-off-by: chaojun-zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun Zhang <chaojun.zhang@intel.com>
Signed-off-by: Chaojun,Zhang <chaojun.zhang@intel.com>
 2026-06-14 19:26:46 -07:00
Noa NeriaandGitHub 1801fad0ba [Bugfix] Stream Llama4 weight loading to avoid host-OOM with copy-returning loaders (#44645) 
Signed-off-by: Noa Neria <nneria@nvidia.com>
 2026-06-14 19:23:44 -07:00
Ting SUNandGitHub 3d6ce816f0 [Bugfix][Model] Validate runai_streamer model_loader_extra_config (#45291) 
Signed-off-by: Ting Sun <suntcrick@gmail.com>
 2026-06-14 19:23:30 -07:00
Taneem IbrahimandGitHub 2c764c089a Added real /v1/embeddings support for messages + chat_template_kw (#45173) 
Signed-off-by: Taneem Ibrahim <taneem.ibrahim@gmail.com>
 2026-06-15 09:08:10 +08:00
Michael MaandGitHub c621af1690 [BugFix] Fix prompt_embeds for multimodal models (#45383) 
Signed-off-by: ruinan ma <r7ma3088@gmail.com>
 2026-06-14 01:44:56 -07:00
Roger WangandGitHub e2bf2b3d84 [Perf] Use bisect for mm feature lookup in model runner v2 (#45566) 
Signed-off-by: Roger Wang <hey@rogerw.io>
 2026-06-14 00:22:53 -07:00
Amanzhol SalykovandGitHub 725c3bc808 [ROCm][Perf] Enable W4A16 FlyDSL MoE (#44400) 
Signed-off-by: amd-asalykov <asalykov@amd.com>
Signed-off-by: Amanzhol Salykov <asalykov@amd.com>
 2026-06-14 00:14:39 -07:00
Marceli FylcekGitHubKunshang Ji
 		9548a1887f [XPU] Support int4 group_size=32 W4A16 MoE (#45136) 
Signed-off-by: Marceli Fylcek <marceli.fylcek@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-06-14 00:14:35 -07:00
Jeff (Junze) MaandGitHub 9fd737badc [Bugfix][DCP] Fix illegal memory access in DCP a2a decode under full CUDA graphs (#45487) 2026-06-14 00:14:31 -07:00
Ekagra RanjanGitHubgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>Harry MellorBenjamin Chislett
 		4ef4492e9b [V1][Spec Decode] Add Dynamic SD (#32374) 
Signed-off-by: Ekagra Ranjan <3116519+ekagra-ranjan@users.noreply.github.com>
Signed-off-by: Benjamin Chislett <chislett.ben@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
 2026-06-14 00:14:27 -07:00
Shengqi ChenGitHubXin LiShawRongChange72
 		78e7293bb1 [Build] Fix CUDA arch build coverage gaps (#45277) 
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Xin Li <xinli-sw@users.noreply.github.com>
Co-authored-by: ShawRong <ShawRong@users.noreply.github.com>
Co-authored-by: Change72 <Change72@users.noreply.github.com>
 2026-06-13 22:09:20 -07:00
achyuthan.sGitHubShengqi Chen
 		54bbf51668 [Bugfix] nightly Docker images crash with ImportError: AnthropicOutputConfig since May 28 (#44795) 
Signed-off-by: achyuthan.s <113010327+Achyuthan-S@users.noreply.github.com>
Signed-off-by: Achyuthan S <achyuthan.sivasankar@gmail.com>
Signed-off-by: Achyuthan Sivasankar <achyuthan.sivasankar@gmail.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
 2026-06-13 21:45:29 -07:00
Nick HillandGitHub cf027b86af [Core] Simplify MRV2 async output handling (#45442) 2026-06-13 18:15:36 -07:00
Wentao YeGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		71b961dd35 [Perf] SM90 cutlass fp8 mm supports odd M by swap_ab, 180~290% kernel performance improvement (#44572) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-13 12:05:45 -07:00
WEI CHENG CHIUGitHubClaude
 		521b88c29e [Bugfix] Reject structured outputs for diffusion decoders with a clear error (#45468) 
Signed-off-by: Wayne Chiu <waynehacking8@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-13 12:04:01 -07:00
Harry MellorandGitHub b3f0a0a0df Fix docs build on main (#45536) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-06-13 08:53:23 -07:00
Juan Pérez de AlgabaandGitHub 470229c37e [Security] Fix DoS via prompt_embeds on M-RoPE models (#45252) 
Signed-off-by: jperezde <jperezde@redhat.com>
 2026-06-13 10:17:38 +00:00
Juan Pérez de AlgabaGitHubHarry Mellor
 		2b3006076c [Security] Add timeout guard for regex compilation in structured outp… (#45118) 
Signed-off-by: jperezde <jperezde@redhat.com>
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-06-13 09:52:56 +00:00
Wentao YeandGitHub 96fa5cdd9e [CI Bug] Fix ValueError: There is no module or parameter named 'model.vision_tower.vision_model' (#45478) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
 2026-06-13 02:38:37 -07:00
Andreas KaratzasandGitHub 9261dbbc55 Treat null completion max_tokens like the default (#45491) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-06-13 09:34:09 +00:00