Commit Graph
15650 Commits
Author SHA1 Message Date
Woosuk Kwon d9b481e248 fix ruff
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-09 02:13:11 +00:00
Woosuk Kwon c8661431e0 minor
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-09 02:05:09 +00:00
Woosuk Kwon bf0d29dddb mtp registry
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-09 01:51:11 +00:00
Woosuk Kwon fdcd95a1a3 update
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 22:22:52 +00:00
Woosuk Kwon 4f1d426261 Rename & fix
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 21:58:38 +00:00
Woosuk Kwon 88fa073594 tmp registry
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 21:39:25 +00:00
Woosuk Kwon a0dd7c27a5 reorg
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 21:28:44 +00:00
Woosuk Kwon 4e05add0af update sparse indexer
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 20:45:16 +00:00
Woosuk Kwon a65a434cc3 Merge branch 'main' into woosuk/ds-exp 2026-04-08 19:01:16 +00:00
Woosuk Kwon c86cb2aeb8 optimize mtp
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 19:01:03 +00:00
e24e0a43a4 [Attention] relax the head dim 512 and paged kv for sm90+FA4 (#38835)
Signed-off-by: Siyuan Fu <siyuanf@nvidia.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-04-08 18:23:18 +00:00
b55d830ec7 [Perf][Kernel] Persistent TopK scheduler: unified CUDAGraph-safe kernel with dynamic per-row dispatch - DeepSeek-V3.2 DSA decode (#37421)
Signed-off-by: LopezCastroRoberto <rocastro@redhat.com>
Signed-off-by: Roberto L. Castro <38211239+LopezCastroRoberto@users.noreply.github.com>
Co-authored-by: Claude Sonnet 4.5 <noreply@anthropic.com>
Co-authored-by: Lucas Wilkinson <LucasWilkinson@users.noreply.github.com>
2026-04-08 13:35:57 -04:00
Woosuk Kwon 62c9357879 silu-mul-fp4 fusion
Signed-off-by: Woosuk Kwon <woosuk@inferact.ai>
2026-04-08 17:14:15 +00:00
75e01a39a1 [Feature] NUMA binding support for GPU workers (#38635)
Signed-off-by: Shengqi Chen <harry-chen@outlook.com>
Co-authored-by: Jason Li <jasonlizhengjian@gmail.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
2026-04-08 09:55:24 -07:00
Or OzeriandGitHub 512c5eb455 [kv_offload+HMA][5/N]: Track group block hashes and block IDs (#37109)
Signed-off-by: Or Ozeri <oro@il.ibm.com>
2026-04-08 19:50:28 +03:00
Flora FengandGitHub 13151a4df4 [Bugfix] Fix Gemma4 streaming tool call corruption for split boolean/number values (#39114)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-08 16:46:27 +00:00
Gregory ShtrasbergandGitHub 56c976c1b5 [ROCm] Enable fused_silu_mul_block_quant on ROCm (#38817)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-04-08 11:23:32 -05:00
d74a306c4b [Core] Use tuple_return in split_module for tuple-conformant subgraphs (#38752)
Signed-off-by: Frederik Gossen <frgossen@meta.com>
Co-authored-by: Boyuan Feng <boyuan@meta.com>
2026-04-08 09:09:58 -07:00
Gregory ShtrasbergandGitHub 0e9f0a516c [ROCm][CI-Build] Cherry pick triton BUFFER_OPS fix and update AITER (#38580)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2026-04-08 10:38:03 -05:00
haosdentandGitHub 8904fc4d19 [Bugfix] Fix V1 logprobs empty strings for multi-byte UTF-8 tokens when logprobs > 0 (#34875)
Signed-off-by: haosdent <haosdent@gmail.com>
2026-04-08 15:30:00 +00:00
nemanjaudovicandGitHub 1a2c17634e [Bugfix] Add missing ASRDataset import and CLI args in benchmarks/throughput.py (#38114)
Signed-off-by: nemanjaudovic <nudovic@amd.com>
2026-04-08 13:53:53 +00:00
Matthew BonanniandGitHub 308cec5864 [FlashAttention] Symlink FA4 instead of copying when using VLLM_FLASH_ATTN_SRC_DIR (#38814)
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
2026-04-08 12:04:34 +00:00
wang.yuqiandGitHub 4e2ab1861d [CI Failure] pin nomic-embed-text-v1 revision (#39292)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2026-04-08 11:43:06 +00:00
140cbb1186 [Bugfix] Cuda Clean up scales Kvcache fp8/int8_per_token_head (#39224)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: Michael Goin <mgoin64@gmail.com>
2026-04-08 04:08:04 -07:00
6155bbd1dd [Bugfix][Docs] Fix ReadTheDocs build crash from mocked torch decorator (#39284)
Signed-off-by: khluu <khluu000@gmail.com>
Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-08 09:43:01 +00:00
rasmithandGitHub 78434b923c [CI][AMD][BugFix][Kernel] Cast induction variable to int64 on MI350 for chunk_gated_delta_rule_fwd_kernel_h_blockdim64 to avoid illegal memory access (#39087)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2026-04-08 16:57:18 +08:00
Michael GoinandGitHub 2488d1dca2 [Docs] Update README (#39251)
Signed-off-by: mgoin <mgoin64@gmail.com>
2026-04-08 11:34:07 +08:00
yokeandGitHub d734445fcd [Bugfix][Frontend] Fix Gemma4 streaming HTML duplication after tool calls (#38909)
Signed-off-by: yoke233 <yoke2012@gmail.com>
2026-04-08 11:03:54 +08:00
Flora FengandGitHub 927975ead8 [Parser] Migrate response api streaming to unified parser (#38755)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
Signed-off-by: Andrew Xia <axia@meta.com>
2026-04-08 10:09:00 +08:00
Flora FengandGitHub 9ea7d670d8 [Bugfix] Fix Qwen3 tool parser for Responses API tools (#38848)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-08 10:08:51 +08:00
7b80cd8ac3 [Docs] Add Phi-4-reasoning-vision to supported models + examples (#39232)
Signed-off-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
Co-authored-by: Varun Sundar Rabindranath <vsundarr@redhat.com>
2026-04-08 02:02:26 +00:00
Andrey TalmanandGitHub 2111997f96 [release 2.11] Update to torch 2.11 (#34644) 2026-04-07 18:55:48 -07:00
Flora FengandGitHub 5af684c319 [CI] Add reasoning parser tests to CI (#37025)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-08 00:57:36 +00:00
Md. Mekayel AnikandGitHub d521dcdbcc docs: clarify SMT and OMP acronyms in CpuPlatform (#39085) 2026-04-07 17:42:07 -07:00
Giancarlo DelfinandGitHub 5daf62271d [Model Runner V2] Fuse probabilistic rejection sample kernels (#38496)
Signed-off-by: Giancarlo Delfin <gdelfin@inferact.ai>
2026-04-07 17:37:37 -07:00
ad3304425b [XPU] add xpu backend implementation of mxfp8 quant (#38682)
Signed-off-by: Zhu, Zufang <zufang.zhu@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-04-08 08:30:35 +08:00
Lucas WilkinsonandGitHub 70406eb1dc [Attention][V0 Deprecation] Deprecate accept output buffer (#39125)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2026-04-07 17:14:58 -04:00
Woosuk Kwon de10041d85 Merge branch 'main' into woosuk/ds-exp 2026-04-07 20:24:15 +00:00
Yubo WangandGitHub 08bfedc152 [Bugfix] Fix extract_hidden_states crash with quantized KV cache dtype (#39160)
Signed-off-by: Yubo Wang <yubowang2019@gmail.com>
2026-04-07 11:18:33 -07:00
Flora FengandGitHub 0102bd2f4c [Parser] Pass request.tools to tool parser (#38860)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
2026-04-08 01:36:21 +08:00
rasmithandGitHub 83d09d36b5 [CI][Bugfix][AMD][ Ensure weights created when using emulating OCP MXFP4 (#36993)
Signed-off-by: Randall Smith <Randall.Smith@amd.com>
2026-04-08 00:37:16 +08:00
92b9afeecd [XPU] Quick fix for TritonMLA to remove cuda hardcode (#39088)
Signed-off-by: Chendi Xue <chendi.xue@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
2026-04-08 00:17:58 +08:00
Jinzhen LinandGitHub 7310555482 [Bugfix] Fix marlin nvfp4 rescaling (#37502)
Signed-off-by: Jinzhen Lin <jinzhen.ljz@antgroup.com>
2026-04-07 08:57:17 -07:00
96b5004b71 [KVConnector] Support 3FS KVConnector (#37636)
Signed-off-by: wuchenxin <wuchenxin.wcx@alibaba-inc.com>
Signed-off-by: ibifrost <47308427+ibifrost@users.noreply.github.com>
Co-authored-by: Simon Mo <simon.mo@hey.com>
2026-04-07 15:46:00 +00:00
kkyyxhllandGitHub 98e1a43af7 [Bugfix][Quantization] Fix PerTensorScale loading with tuple shard_id in MergedColumnParallelLinear (#38517)
Signed-off-by: loukang <loukang@xiaohongshu.com>
2026-04-07 11:16:26 -04:00
729eb59f60 [KVConnector]: prioritize external connector over internal registry (#38301)
Signed-off-by: baoloongmao <baoloongmao@tencent.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2026-04-07 15:03:11 +00:00
Ilya BoytsovandGitHub 6e1100889e fix(test): recompute Jina ColBERT rotary inv_freq cleared by transformers v5 weight loader (#39176)
Signed-off-by: Ilya Boytsov <ilyaboytsov1805@gmail.com>
2026-04-07 22:40:55 +08:00
edcc37a8ce Fix Mistral yarn warning in Transformers v5 (#37292)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Co-authored-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
2026-04-07 13:23:33 +00:00
Harry MellorandGitHub 79df4a794d Automatically add links to API docs for matching strings in docs (#37434)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2026-04-07 21:21:18 +08:00
Ronen SchafferandGitHub 7c139ab23f [KV Offload] Clean up ARC/LRU refactoring leftovers: group ARC tests and fix stale comment (#38217)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
2026-04-07 15:14:45 +03:00