karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 1 Packages Activity
18,530 Commits 354 Branches 175 Tags
e97c3cb303f9ba54ed1c73b14f880760cfdfd344
Commit Graph
18530 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Nils MattesonGitHubNils Mattesonmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		e97c3cb303 [Core] Persist and reuse the memory-profiling result across boots (opt-in) (#47388) 
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-08 00:53:02 +00:00
Rohan PotdarGitHubClaude Opus 4.8
 		4aceabf8c1 [ROCm][Bugfix] Key sparse-MLA persistent metadata on per-request context lengths (#47766) 
Signed-off-by: Rohan Potdar <rohan.potdar@amd.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-07 19:22:34 -05:00
stefankoncarevicandGitHub 6e35c5e5af [ROCm][CI] Minimize comment in RocmAttention q_scale check (#47731) 
Signed-off-by: stefankoncarevic <stefan.koncarevic@amd.com>
 2026-07-07 19:16:08 -05:00
Ameen PatelGitHubAmeenPClaude
 		aad0fb741b [CI/Build] Accept ready-run-all-tests label in pre-commit gate (#47897) 
Signed-off-by: AmeenP <ameen@primeintellect.ai>
Co-authored-by: AmeenP <ameen@primeintellect.ai>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-07-07 23:18:59 +00:00
yzong-rhandGitHub 7d2ce5750e [Bugfix] Patch Hopper MXFP4 OOB scales reads leading to NaN (#47910) 
Signed-off-by: Yifan Zong <yzong@redhat.com>
 2026-07-07 22:51:22 +00:00
Juan Pérez de AlgabaandGitHub 675f4295cd fix(security): bound completion prompt list to prevent unbounded engine fan-out (#47845) 
Signed-off-by: jperezde <jperezde@redhat.com>
 2026-07-07 22:48:20 +00:00
Jason LiandGitHub d99adcebdc [BugFix] Fix ModelOpt quantization inference for fused siblings (#47445) 
Signed-off-by: jasonlizhengjian <jasonlizhengjian@gmail.com>
 2026-07-08 03:19:42 +05:00
vanshbhatia-amdGitHubvanshbhatia-amd
 		c8c2f838e7 Add tuned selective_state_update config for AMD Instinct MI355 (#47767) 
Signed-off-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
Co-authored-by: vanshbhatia-amd <210711135+vanshbhatia-amd@users.noreply.github.com>
 2026-07-07 22:19:08 +00:00
Nils MattesonGitHubNils Mattesonmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		dd0d74cd92 [Doc] Surface the --kv-cache-memory suggestion at INFO and document fast-startup knobs (#47374) 
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-07 15:05:07 -07:00
Sahil KadadekarGitHubClaude Fable 5
 		55da232db6 [Bugfix] Pad Mamba page size instead of scaling block_size in unify_kv_cache_spec_page_size (#45207) 
Signed-off-by: Sahil170595 <147995121+Sahil170595@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-07 22:01:34 +00:00
Wentao YeandGitHub 3f99883d97 [CI Bug Fix] Temp fix for v3.2 accuracy (#47902) 2026-07-07 16:36:03 -04:00
Nick CaoandGitHub 47c40bfe8a [Doc] Fix manylinux tag in installation guide (#47913) 
Signed-off-by: Nick Cao <ncao@redhat.com>
 2026-07-07 20:34:05 +00:00
Matthew BonanniGitHubClaude Opus 4.8
 		3dd910da42 [Bugfix] Allow non-contiguous query in FlashInfer FP8 query quantization (#47908) 
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
 2026-07-07 20:11:34 +00:00
Benjamin ChislettandGitHub 7bd154375d [Bugfix] Fix mamba+dflash for MRV2 (#47698) 2026-07-07 15:59:13 -04:00
Rishabh SainiandGitHub 2f3f441f84 fix: include topic frame in KV events replay response (#45177) 
Signed-off-by: RishabhSaini <rishabhsaini01@gmail.com>
 2026-07-07 14:48:23 -04:00
Nils MattesonGitHubNils Matteson
 		d6875196ad [Bugfix] Exclude kv_cache_memory_bytes from CacheConfig.compute_hash (#47356) 
Signed-off-by: Nils Matteson <nils@thaw.sh>
Signed-off-by: Nils Matteson <nilsmatteson@icloud.com>
Co-authored-by: Nils Matteson <nils@thaw.sh>
 2026-07-07 10:46:51 -07:00
Sting LinandGitHub abe41f28de Upgrade tpu-inference to v0.24.0 (#47835) 
Signed-off-by: StingLin <sting.lin@cienet.com>
 2026-07-07 17:15:32 +00:00
Roberto L. CastroandGitHub c3284c31f5 [Perf][3/N] Expand Triton kernel warmup coverage, Qwen (#47546) 
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
 2026-07-07 17:06:59 +00:00
RobinandGitHub c74e751824 [Doc] Fix grammatically incorrect error message in gpu_worker and xpu_worker (#36715) 
Signed-off-by: Hongbin10 <jdmjdm1998@163.com>
 2026-07-07 17:03:06 +00:00
liuzhenweiandGitHub b93cbd7416 [XPU] Fix topk_sigmoid arg mismatch on XPU (#47858) 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
 2026-07-07 16:53:18 +00:00
Wentao YeGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		bdc6f3bfa1 [Bug] Fix tmp directory for lm_eval (#47755) 
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-07 16:40:12 +00:00
Ameen PatelGitHubClaudemergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		392d1b4d2e [BugFix][LoRA] Refresh punica metadata when LoRA slots are reassigned under an unchanged mapping (#47725) 
Signed-off-by: AmeenP <ameenp360@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-07 08:53:55 -07:00
Simon MoGitHubCursor AgentBenjamin Chislett
 		21b396abe1 AGENTS MD: Add suggestion on how to incorporate tests (#47784) 
Signed-off-by: Simon Mo <simon.mo@hey.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: Benjamin Chislett <chislett.ben@gmail.com>
 2026-07-07 08:16:08 -07:00
liuzhenweiandGitHub bdaf27519f [XPU] Fix Event init failure w/ blocking (#47868) 
Signed-off-by: zhenwei-intel <zhenwei.liu@intel.com>
 2026-07-07 22:54:03 +08:00
Eldar KurtićandGitHub beb4327c46 Enable causal masking for SWA in vllm-project/speculators models (#47745) 
Signed-off-by: Eldar Kurtic <8884008+eldarkurtic@users.noreply.github.com>
 2026-07-07 10:24:14 -04:00
Chang GuoGitHubClaude Opus 4.8Or Ozeri
 		c46ced1ee3 [kv_offload] Establish tier-owned KV event handling (#46544) 
Signed-off-by: Change72 <changg@nvidia.com>
Signed-off-by: Chang Guo <changg@nvidia.com>
Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
 2026-07-07 16:55:20 +03:00
Dakai AnGitHubNick Hill
 		65dcde1695 [Bugfix] Fix PD disagg + MTP correctness for Qwen3.5(GDN) (#47466) 
Signed-off-by: Dakai An <dakaian108@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-07-07 13:51:22 +00:00
Pierangelo Di PilatoGitHubOr Ozeri
 		65a7b46284 [KV-Offloading] Support workload identity for objectstore secondary tier (#47063) 
Signed-off-by: Pierangelo Di Pilato <pierdipi@redhat.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
 2026-07-07 16:30:16 +03:00
Tyler Michael SmithGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>Claude Opus 4.6
 		93e2ab7111 Disable dynamic speculative decoding when DP is enabled (#45963) 
Signed-off-by: Tyler Michael Smith <tlrmchlsmth@gmail.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
 2026-07-07 12:52:41 +00:00
Lanze LiuandGitHub 8b745527cd [Bugfix] Fix UBatchWrapper CUDA graph key to sum all ubatches, not just first two (#43161) 
Signed-off-by: Lanze Liu <lanzetech@gmail.com>
 2026-07-07 12:42:31 +00:00
Nick CaoGitHubClaude
 		920469974a [UX] Log worker exit code when process dies unexpectedly (#38641) 
Signed-off-by: Nick Cao <ncao@redhat.com>
Co-authored-by: Claude <noreply@anthropic.com>
 2026-07-07 12:36:29 +00:00
Ting SUNGitHubNick Hill
 		8b91cd5b20 [Bugfix][Core] Close underlying iterator in merge_async_iterators single-iterator fast path (#44726) 
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
 2026-07-07 05:13:41 -07:00
Harry MellorandGitHub dd94484577 Bump Transformers version to 5.10.4 (#41359) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-07-07 05:13:28 -07:00
Shaun KotekandGitHub 7ff656cc8b fix: ensure no double load of lm head in nemotron mtp (#47440) 
Signed-off-by: Shaun Kotek - Nvidia <skotek@nvidia.com>
 2026-07-07 12:01:45 +00:00
danielafrimiandGitHub 0a2965b1b3 [BugFix] Fix ModelOpt mixed-precision quantization for sparse quantized_layers configs. (#47318) 
Signed-off-by: Daniel Afrimi <dafrimi@nvidia.com>
Signed-off-by: <dafrimi@nvidia.com>
 2026-07-07 11:45:13 +00:00
Harry MellorandGitHub 0ed05b6f82 [CI] Fix Transformers modeling backend LoRA test (#47832) 
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
 2026-07-07 11:40:00 +00:00
Guan-Ming ChiuandGitHub ed051fab54 [Bugfix] Reject sampling params unsupported by diffusion models (#45418) 
Signed-off-by: Guan-Ming (Wesley) Chiu <105915352+guan404ming@users.noreply.github.com>
 2026-07-07 11:25:36 +00:00
Ronen SchafferGitHubOr Ozeri
 		48fcfc926c [KV Offload] Add ParentManager ABC for secondary tier callbacks (#47274) 
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
 2026-07-07 13:51:18 +03:00
drakoshaGitHubClaudeOr Ozeri
 		3354dba381 [Bugfix][KV offload] Store interior chunk-boundary blocks under MTP/Eagle (#46972) 
Signed-off-by: Mikhail Kostryukov <mike@triptrack.net>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Or Ozeri <oro@il.ibm.com>
 2026-07-07 13:16:52 +03:00
Andreas KaratzasGitHubRohan138CodexMicah WilliamsonMatthew Wong
 		cbb5f045be [ROCm][CI] Refresh ROCm base images when docker rocm_base changes (#46904) 
Signed-off-by: Rohan138 <rohanpotdar138@gmail.com>
Signed-off-by: Codex <codex@example.invalid>
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
Signed-off-by: Matthew Wong <Matthew.Wong2@amd.com>
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
Co-authored-by: Rohan138 <rohanpotdar138@gmail.com>
Co-authored-by: Codex <codex@example.invalid>
Co-authored-by: Micah Williamson <micah.williamson@amd.com>
Co-authored-by: Matthew Wong <Matthew.Wong2@amd.com>
 2026-07-07 03:10:50 -07:00
Juan Pérez de AlgabaGitHubCursor
 		b3e85be663 fix: use configured max_logprobs instead of hardcoded 20 in derender validation (#47834) 
Signed-off-by: jperezde <jperezde@redhat.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
 2026-07-07 09:42:47 +00:00
Summer YangandGitHub d3e69fd671 [Perf] Use blocking CUDA events to avoid busy polling cuda driver lock (#47081) 
Signed-off-by: Jingyi Yang <girasoleyang@gmail.com>
 2026-07-07 09:36:10 +00:00
Rukhaiya2004GitHubAkash KaothalkarAkash Kaothalkar
 		c85d72076a [HARDWARE][POWER] optimize math functions of VSX power (#47321) 
Signed-off-by: Akash Kaothalkar <akashkaothalkar@akashs-mbp.bl1-in.ibm.com>
Signed-off-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
Signed-off-by: Akash kaothalkar <akash.kaothalkar@ibm.com>
Signed-off-by: Rukhaiya <bibirukhaiya123@gmail.com>
Co-authored-by: Akash Kaothalkar <akashkaothalkar@akashs-mbp.bl1-in.ibm.com>
Co-authored-by: Akash Kaothalkar <akash.kaothalkar@ibm.com>
 2026-07-07 09:35:47 +00:00
Kyung Sub Lee (Daniel)GitHubClaude Fable 5
 		c5b66233b2 [Bugfix][Spec Decode] Skip uniform spec-decode padding for diffusion models (#47464) 
Signed-off-by: kl527 <kl527@cornell.edu>
Signed-off-by: Kyung Sub Lee (Daniel) <66861800+kl527@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
 2026-07-07 09:25:12 +00:00
Netanel HaberGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		066f02ae94 [MoE] FI autotuning: max bucket = max token count [e.g. DP_size*MNBT] (#47427) 
Signed-off-by: Netanel Haber <58652339+netanel-haber@users.noreply.github.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 2026-07-07 12:08:36 +03:00
Jee Jee LiandGitHub 5d23ca47ab [Kernel] Applies routed_scaling_factor internally (#47408) 
Signed-off-by: Jee Jee Li <jeejeelee@inferact.ai>
 2026-07-07 02:00:54 -07:00
Bugen ZhaoGitHubmergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
 		e55cc59e52 [Rust Frontend][CI] Unblock more end-to-end test cases (#47735) 
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
 2026-07-07 08:27:20 +00:00
Gabriel WuGitHubClaude Fable 5Shengqi Chen
 		ba50b9763f [Bugfix] Match the mapped filename in find_loaded_library (#47586) 
Signed-off-by: Zihua Wu <13583761+lucifer1004@users.noreply.github.com>
Co-authored-by: Claude Fable 5 <noreply@anthropic.com>
Co-authored-by: Shengqi Chen <harry-chen@outlook.com>
 2026-07-07 08:06:29 +00:00
Ting SUNGitHubNick Hillchaunceyjiang
 		b4cfbc24d3 [Bugfix][Core] Fix host memory leak from undrained new_block_ids (#44490) 
Signed-off-by: Ting Sun <suntcrick@gmail.com>
Signed-off-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: Nick Hill <nickhill123@gmail.com>
Co-authored-by: chaunceyjiang <chaunceyjiang@gmail.com>
 2026-07-07 07:32:55 +00:00
Aritra Roy GosthipatyandGitHub 1e823dc01d [docs update] Update usage of hf cli for cache list and removal (#47830) 
Signed-off-by: Aritra Roy Gosthipaty <aritra.born2fly@gmail.com>
 2026-07-07 07:09:18 +00:00