karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity
18,237 Commits 354 Branches 175 Tags
dependabot/github_actions/actions/setup-python-6.3.0
Commit Graph
18237 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Jee Jee LiandGitHub 9f6f296428 [CI/Build] Remove BaiChuanForCausalLM from the LoRA test (#46494) 
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
 2026-06-23 22:09:48 +08:00
lchengGitHubJee Jee LiJee Jee Li
 		e51e700470 [LoRA] Gate all_gather on fully_sharded_loras inside _mcp_apply; rewrite regression test (#45715) 
Signed-off-by: lcheng <lcheng321@gatech.edu>
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <jeejeelee@inferact.ai>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
 2026-06-23 07:08:33 -07:00
yzong-rhGitHubBen Browning
 		f59db63732 [Bugfix] GPT-OSS Autodrop reasoning in Response API and cleanup (#45048) 
Signed-off-by: Yifan Zong <yzong@redhat.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
 2026-06-23 09:36:33 -04:00
Rukhaiya2004andGitHub 9f5117820f [HARDWARE][POWER] Enable fp16 support for PowerPC (#46135) 
Signed-off-by: Rukhaiya <bibirukhaiya123@gmail.com>
 2026-06-23 13:24:49 +00:00
Muhammad FawazGitHubMahad Rehmann
 		1bf149f334 Filter Pydantic-internal markers from validation error param (#46457) 
Signed-off-by: muhammadfawaz1 <135441198+muhammadfawaz1@users.noreply.github.com>
Co-authored-by: Mahad Rehmann <114791389+mahadrehmann@users.noreply.github.com>
 2026-06-23 13:20:50 +00:00
yzong-rhGitHubBen Browning
 		2a675a7b9f [Bugfix] Responses API assistant EasyInputMessageParam input (#44361) 
Signed-off-by: Yifan Zong <yzong@redhat.com>
Co-authored-by: Ben Browning <bbrownin@redhat.com>
 2026-06-23 08:54:46 -04:00
Itay EtelisGitHubItay EtelisItay Etelis
 		7d47cff933 [Bugfix][KV Offload] Fix swap_blocks_batch on the default stream (#46379) 
Signed-off-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <itay.etelis@ibm.com>
Co-authored-by: Itay Etelis <Itay.etelis@gmail.com>
 2026-06-23 05:45:27 -07:00
Srinivas KrovvidiGitHubsrinivas_oo7
 		091bc1026e [KV Offloading] Add tiering metric plumbing (#45959) 
Signed-off-by: srinivas_oo7 <sklinkedin0120@gmail.com>
Co-authored-by: srinivas_oo7 <sklinkedin0120@gmail.com>
 2026-06-23 15:10:36 +03:00
hillel.darshanGitHubCursor
 		3554ada5d8 [CPU][Bugfix][Speculative Decoding] Accept USE_FP64_GUMBEL in CPU recovered-tokens sampler (#46069) 
Signed-off-by: hillel.darshan <hillel.darshan@intel.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-06-23 11:54:07 +00:00
wang.yuqiandGitHub 31ca9504b1 [Frontend] Split ServingRender into renderer and entrypoint. (#44285) 
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
 2026-06-23 11:19:09 +00:00
Tan Pin SiangGitHubvllmellmHongxia YangJun Kang ChowChun FangTianDi101functionstackxtjtanaa
 		d32575a2d2 [ROCm][P/D] Support MoRIIO heterogeneous TP fan-in (#46332) 
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Jun Kang Chow <junkangchow@gmail.com>
Co-authored-by: Chun Fang <chun.fang@amd.com>
Co-authored-by: TianDi101 <ditian12@amd.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
Co-authored-by: tjtanaa <tunjian.tan@embeddedllm.com>
 2026-06-23 10:33:23 +00:00
Juan Pérez de AlgabaandGitHub 83fa302ca4 fix(security): prevent infinite loop in split_audio with NaN audio sa… (#46463) 2026-06-23 10:24:51 +00:00
frida-anderssonandGitHub 20b5af55c1 [ROCm][Perf] DSv3.2: fuse MLA Q concat+fp8-quant in forward_mqa (#43673) 
Signed-off-by: Frida Andersson <fanderss@amd.com>
 2026-06-23 18:12:04 +08:00
Qiming ZhangandGitHub 901a3b091c fix gpt_oss pp>1 with ep (#46441) 
Signed-off-by: mayuyuace <qiming1.zhang@intel.com>
 2026-06-23 16:59:11 +08:00
ReidGitHubBugen Zhao
 		2d721ab5d8 [Rust Frontend] Align Rust allowed_token_ids validation with Python (#46348) 
Co-authored-by: Bugen Zhao <i@bugenzhao.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-06-23 08:32:33 +00:00
ReidGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		accaa434f3 [Rust Frontend] Support echo for token-ID completion prompts (#46219) 
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: reidliu41 <reid201711@gmail.com>
 2026-06-23 08:04:41 +00:00
Sunny YuanandGitHub a04654da23 Doc: fix missing GLM-5.x in supported models (#46452) 
Signed-off-by: Sunny Yuan <y.zichen@wustl.edu>
 2026-06-23 07:42:27 +00:00
Bugen ZhaoandGitHub 25bc3be49c [Rust Frontend] Correct --reasoning-parser semantics (#46359) 
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-06-23 15:38:39 +08:00
Ting SUNandGitHub a46f3eb232 [Bugfix][Model Runner V2] Preserve all allowed_token_ids in the logit bias kernel (#46245) 
Signed-off-by: Ting Sun <suntcrick@gmail.com>
 2026-06-23 07:01:13 +00:00
jackGitHubQwertyJackChauncey
 		6c427dd401 [BugFix] Omit empty tool_calls from OpenAI chat responses (#44105) 
Signed-off-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Signed-off-by: Chauncey <chaunceyjiang@gmail.com>
Co-authored-by: QwertyJack <7554089+QwertyJack@users.noreply.github.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
 2026-06-23 13:43:53 +08:00
ChaunceyGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		3ce5823762 [Refactor] Responses API parser state into conversation context (#46030) 
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-23 13:42:58 +08:00
Woosuk KwonandGitHub 04c2a8deac [DeepEP V2] Fill invalid recv_topk_idx with -1 (#46432) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
 2026-06-22 21:45:49 -07:00
Tan Pin SiangGitHubvllmellmHongxia YangJun Kang ChowChun FangTianDi101functionstackx
 		7e47fb72b5 [ROCm][P/D] Fix MoRIIO WRITE mode for mixed KV layouts (#46290) 
Signed-off-by: Tan Pin Siang <tanpinsiang@gmail.com>
Co-authored-by: vllmellm <vllm.ellm@embeddedllm.com>
Co-authored-by: Hongxia Yang <hongxia.yang@amd.com>
Co-authored-by: Jun Kang Chow <junkangchow@gmail.com>
Co-authored-by: Chun Fang <chun.fang@amd.com>
Co-authored-by: TianDi101 <ditian12@amd.com>
Co-authored-by: functionstackx <47992694+functionstackx@users.noreply.github.com>
 2026-06-23 12:12:51 +08:00
Bugen ZhaoGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		a8481be7a9 [Rust Frontend][Perf] Use dedicated runtime for HTTP/request-processing/ZMQ (#46051) 
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-06-23 04:03:20 +00:00
Kunshang JiandGitHub 9d3317172c [XPU][CI]fix xpu kv cache layout test (#46429) 
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
 2026-06-23 03:43:29 +00:00
Dao007foreverGitHubClaude Opus 4.8
 		430a95ae3a [v1][kvcache] Honor prefix-cache retention interval for Mamba/linear attention (#45845) 
Signed-off-by: Dao Le <daole@inferact.ai>
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 19:51:11 -07:00
Mike GandGitHub 56e5797511 [Quant] Enable modelopt_mixed on Turing (SM75) (#45375) 
Signed-off-by: Mike G <180722391+mikekg@users.noreply.github.com>
 2026-06-22 19:30:49 -07:00
Rui YinGitHubabinggo
 		8db12169a4 fix: stream Qwen3 tool call string arguments (#46351) 
Signed-off-by: Rui Yin <2260891073@qq.com>
Co-authored-by: abinggo <107740309+abinggo@users.noreply.github.com>
 2026-06-23 10:26:37 +08:00
MichaelCaooGitHubClaude
 		33f50773cb [Doc] Fix typos, grammar, and broken commands across docs (#46398) 
Signed-off-by: MichaelCaoo <a992033227@163.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-23 02:01:22 +00:00
Micah WilliamsonandGitHub fa36f86d77 [CI] Torch 2.11 flaky test_spec_decode_logprobs and gritlm tests (#45772) 
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
 2026-06-23 01:26:54 +00:00
Michael GoinGitHubClaude Opus 4.8
 		8207ce0850 [Bugfix] Fix humming lm_head crash and FusedMoE weight_shape coercion (#46420) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-06-22 18:19:29 -07:00
Woosuk KwonGitHubRoy WanggnovackClaudemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		e48592066e [DeepEP V2] Bound num_max_tokens_per_rank in do_expand=False (#46404) 
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
Co-authored-by: Roy Wang <jasonailu87@gmail.com>
Co-authored-by: gnovack <novackgm@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-22 18:14:53 -07:00
stefankoncarevicGitHubAndreas Karatzas
 		91ba720b75 [ROCm][CI] Only require q_scale==1.0 for fp8 query in RocmAttention (#46148) 
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
 2026-06-22 18:25:43 -05:00
fxmarty-amdandGitHub 6ead164e52 [CI] Add TP=4 requirement to test_mixed_precision_model_accuracies (#46161) 
Signed-off-by: Felix Marty <Felix.Marty@amd.com>
 2026-06-22 18:19:43 -05:00
Bowen BaoGitHubAndreas Karatzas
 		c97e8f99d6 [ROCm][Quantization][4/N] refactor quark_moe fp8 w/ oracle (#43721) 
Signed-off-by: Bowen Bao <bowenbao@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
 2026-06-22 15:58:03 -07:00
Guipeng ZhangGitHubCodexMichael Goin
 		183b5f27ea [Bugfix][V1][TurboQuant] Reserve workspace before CUDA graph capture (#44053) 
Signed-off-by: Guipeng Zhang <zhangguipeng23z@ict.ac.cn>
Co-authored-by: Codex <codex@openai.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-06-22 15:47:48 -07:00
ZewenShen-CohereGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		ca5b24695b Fix static actorder handling for compressed-tensors WNA16 MoE (#41161) 
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-22 15:46:46 -07:00
Charlie FuandGitHub 6f6bd3b8fe [ROCm][CI] Increase the max wait time for server startup (#46417) 
Signed-off-by: charlifu <charlifu@amd.com>
 2026-06-22 17:46:31 -05:00
Andreas KaratzasandGitHub 70ef4d3009 [ROCm][CI] Purging away redundant test group definitions (#46418) 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
 2026-06-22 15:42:47 -07:00
Tyler Michael SmithGitHubClaude
 		e2fe837572 [CI] Fix CPU-Multi-Modal Model Tests timeout by adding a 4th shard (#46388) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-06-22 22:08:00 +00:00
Aarushi JainandGitHub fbf9ff7cf4 [CI][ROCm] Restrict MLA cross-layer KV cache test to supported backends on ROCm (#46401) 
Signed-off-by: aarushjain29 <Aarushi.Jain2@amd.com>
 2026-06-22 17:05:26 -05:00
Michael GoinGitHubClaude Opus 4.8
 		6cc2c9ba3a [CI] Add DGX Spark GPQA smoke test (#39541) 
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-22 14:52:38 -07:00
VarshithGitHubClaudeMichael Goin
 		c0b2d8f471 [Bugfix] FusedMoE: coerce shape-(1,) per-tensor scales to 0-D scalar … (#43362) 
Signed-off-by: Varshith <kvarshithgowda@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
 2026-06-22 13:26:53 -07:00
Mohammad Miadh AngkadandGitHub d1a38c2762 [Kernel][Performance] Add FlashInfer cutedsl NVFP4 GEMM backend (#42235) 
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
 2026-06-22 16:17:18 -04:00
stefankoncarevicGitHubAndreas Karatzas
 		2b4a7491ec [ROCm][CI] Query total device memory via amdsmi to avoid HIP init (#46141) 
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
Co-authored-by: Andreas Karatzas <akaratza@amd.com>
 2026-06-22 15:12:24 -05:00
SaddssandGitHub 82ede09a5a [Bugfix][KVConnector] Fix SimpleCPUOffloadConnector GPU->CPU store race (#46278) 2026-06-22 13:08:47 -07:00
Nick HillandGitHub fbf520cf3a [MRV2] Generalize use of WhisperModelState (#46096) 
Signed-off-by: Nick Hill <nickhill123@gmail.com>
 2026-06-22 12:40:02 -07:00
Gabriel WuGitHubClaude Opus 4.8Yongye Zhu
 		44d95069e9 Enable DeepSeek V4 and GLM-5.1 on SM120 (#43477) 
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Yongye Zhu <zyy1102000@gmail.com>
 2026-06-22 11:54:14 -07:00
Dao007foreverGitHubClaude Opus 4.8
 		3ce15fd574 [v1][kvconnector] DecodeBenchConnector: fill list/tuple (Mamba/KDA) KV caches (#45080) 
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
 2026-06-22 11:54:00 -07:00
Jinzhen LinGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		e4b3da3feb [Quantization][CI] add humming lm-eval test (#43752) 
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-06-22 11:23:55 -07:00