Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86

Mono Color

• afa5b7ca0b [Misc][gpt-oss] guard import when triton kernel when not up to date (#22584) Zhewen Li 2025-08-10 21:29:35 -07:00
• 1b99028069 [Misc][gpt-oss] Add rules to label gpt-oss related PRs (#22600) Lifans 2025-08-10 19:49:51 -07:00
• 5898b135ab [BugFix] Fix KVConnectorOutput TPU breakage (#22598) Nick Hill 2025-08-10 19:33:48 -07:00
• b799f4b9ea [CI/Build] Fix tensorizer test for load_format change (#22583) 22quinn 2025-08-10 19:30:00 -07:00
• 06da44f0cb Migrate LlavaImageInputs to TensorSchema (#21770) Benji Beck 2025-08-10 19:29:19 -07:00
• a554991748 Migrate LlavaNextVideoPixelInputs to TensorSchema (#21843) Benji Beck 2025-08-10 19:29:16 -07:00
• d1af8b7be9 enable Docker-aware precompiled wheel setup (#22106) Doug Smith 2025-08-10 19:29:02 -04:00
• 68b254d673 Fix TensorSchema validation test for symbolic dims (#22366) Benji Beck 2025-08-10 10:16:44 -07:00
• 8c50d62f5a Remove redundant row_indices unsqueeze operation in MiniCPMO (#22528) ZiTian Zhao 2025-08-11 00:20:00 +08:00
• b4e2916721 Migrate LlavaNextImageInputs to TensorSchema (#21774) Benji Beckandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-08-10 09:05:21 -07:00
• 65a7917be4 Fix(benchmarks): allow multiple mm contents in OpenAI Chat Completion Benchmarks (#22534) Breno Baldas Skuk 2025-08-10 18:03:15 +02:00
• b76753f0b5 [Bugfix][Kernel] Support partial rotary embedding for MRoPE triton kernel (#22593) Isotr0py 2025-08-11 00:00:36 +08:00
• b81fe83b2c [doc] add alibaba cloud as sponsor (#22597) youkaichao 2025-08-10 23:13:47 +08:00
• 0757551c96 [doc] add beijing meetup links (#22596) youkaichao 2025-08-10 22:51:36 +08:00
• 8290d15d2c Move CacheConfig from config/__init__.py to config/cache.py (#22586) Harry Mellor 2025-08-10 15:36:40 +01:00
• 049c245143 [Misc] Replace flaky image urls in pixtral test (#22574) Isotr0py 2025-08-10 21:18:21 +08:00
• 00976db0c3 [Docs] Fix warnings in docs build (#22588) Harry Mellor 2025-08-10 13:49:51 +01:00
• d411df0296 [Misc] Further refine type annotations in parallel state (#22499) Cyrus Leung 2025-08-10 20:49:48 +08:00
• 010e0e39ea [Doc] Fix API doc link in side navigation (#22585) 22quinn 2025-08-10 01:35:22 -07:00
• 326976291b [Misc] code clean duplicate set_current_vllm_config in _set_vllm_config (#22566) Ning Xie 2025-08-10 15:08:48 +08:00
• 7e8d685775 [Minor] Fix pre-commit error on main (#22579) Isotr0py 2025-08-10 15:08:23 +08:00
• c49848396d Refactor sliding window configuration to Transformers best practice (#21927) Harry Mellor 2025-08-10 04:50:48 +01:00
• 2a84fb422f [TPU] kv cache update kernel doesn't need to be padded slices to multiple of num_slices_per_block (#22394) Chengji YaoandChengji Yao 2025-08-09 20:49:04 -07:00
• 534c45b962 Improve fast_topk function with type hints and documentation (#22530) ZiTian Zhao 2025-08-10 11:25:42 +08:00
• 3d7363e61c [Config] add "qwen" as a native eagle3 target supported model (#22333) Le Chen 2025-08-10 11:21:05 +08:00
• 0c5254b82a [oss] Init gpt-oss bf16 support (#22508) Jee Jee Li 2025-08-10 11:19:13 +08:00
• 61f67d8acd [V1] [Hybrid] Enable Full CUDA Graph (decode-only) for Mamba layers (#21401) Thomas Parnell 2025-08-10 05:16:11 +02:00
• 42172ad18f [FEAT] [Performance] Add triton mrope to replace the torch code path (#22375) TJian 2025-08-09 11:50:03 -07:00
• fbd8595c5c [Bugfix] Fix basic models tests hanging due to mm processor creation (#22571) Isotr0py 2025-08-10 02:42:21 +08:00
• 5a16fa614c [Model] Gemma3n MM (#20495) 3 people 2025-08-09 18:56:25 +02:00
• 2d18256e47 Move ParallelConfig from config/__init__.py to config/parallel.py (#22565) Harry Mellor 2025-08-09 16:33:46 +01:00
• 56186474f6 [Docs] Reduce noise in docs and --help from the JSON tip (#22567) Harry Mellor 2025-08-09 16:31:32 +01:00
• 1bf5e1f25b [CI] [Hybrid] Speed up hybrid models test by removing large models (#22563) Thomas Parnell 2025-08-09 11:04:42 +02:00
• a6022e6fbc GLM-4.5V with new class name at transformers (#22520) Yuxuan ZhangandIsotr0py 2025-08-09 15:50:21 +08:00
• 2be07a0db1 Update docs for Minimax-Text support (#22562) Thomas Parnell 2025-08-09 09:18:18 +02:00
• 0edc0cd52b [Bugfix] Fix CI moe kernel failure (#22556) Jee Jee Li 2025-08-09 15:03:29 +08:00
• 7920e9b1c5 [Bugfix] Fix failing GPT-OSS initialization test (#22557) Isotr0py 2025-08-09 15:03:26 +08:00
• b7c0942b65 [ROCm][Misc] Rename the context_len to seq_len in ROCm custom paged attention kernel (#22097) Charlie Fu 2025-08-09 01:15:06 -05:00
• 9a0c5ded5a [TPU] Add support for online w8a8 quantization (#22425) Kyuyeun Kim 2025-08-08 23:12:54 -07:00
• 10a02535d4 Fix loading of quantized BigCode models (#22463) Eldar Kurtić 2025-08-09 08:12:12 +02:00
• 65552b476b [Misc] Use config definitions from Transformers library (#21913) Cyrus Leung 2025-08-09 14:10:51 +08:00
• 7ad7adb67f v1: Pass KVConnectorOutput to scheduler-side (#22157) Or Ozeri 2025-08-09 09:09:51 +03:00
• 6ade99eafa [V1] [Hybrid] Support Minimax-Text-01 in V1 (#22151) Thomas Parnell 2025-08-09 08:08:48 +02:00
• 3157aebb63 [Log] Add Warning for Deprecation of DeepGEMM old version (#22194) Wentao Ye 2025-08-09 02:07:48 -04:00
• 8a0ffd6285 Remove mamba_ssm from vLLM requirements; install inside test container using --no-build-isolation (#22541) Thomas Parnell 2025-08-09 08:05:32 +02:00
• 23472ff51c [Doc] Add usage of implicit text-only mode (#22561) Roger WangandFlora Feng 2025-08-08 23:04:19 -07:00
• 08b751ba74 Implicit language-model-only mode via limit-mm-per-prompt (#22299) +1020 people 2025-08-08 22:21:40 -07:00
• 429e4e2d42 [Bugfix] Fix ModernBert cuda graph capturing in v1 (#21901) Isotr0py 2025-08-09 13:17:22 +08:00
• 35afe1b30b [BugFix] [P/D] Handle lookahead token count edge-case with Eagle Spec Decoding and P/D (#22317) 3 people 2025-08-08 20:04:15 -04:00
• 81c57f60a2 [XPU] upgrade torch 2.8 on for XPU (#22300) Kunshang Ji 2025-08-09 08:03:45 +08:00
• 311d875614 Drop flaky test_healthcheck_response_time (#22539) Russell Bryant 2025-08-08 19:56:47 -04:00
• e3edc0a7a8 Extract CompilationConfig from config.py (#22524) Harry Mellor 2025-08-09 00:34:25 +01:00
• baece8c3d2 [Frontend] Add unix domain socket support (#18097) yyweiss 2025-08-09 02:23:44 +03:00
• 2fcf6b27b6 [Docs] fix broken links in metrics.md (#22315) Guy StoneandHarry Mellor 2025-08-08 19:22:35 -04:00
• 41b9655751 Skip Qwen 1 in CI because remote code is no longer compatible with Transformers (#22536) Harry Mellor 2025-08-09 00:20:58 +01:00
• bd875d2eb7 [Bugfix] Update FA commit hash (#22546) Thomas Parnell 2025-08-09 01:10:25 +02:00
• f703b923f3 [Misc] DeepGEMM : Avoid JIT generation in the hot-path (#22215) Varun Sundar RabindranathandVarun Sundar Rabindranath 2025-08-08 19:09:59 -04:00
• cd9b9de1fb [BugFix] Fix IMA FlashMLA full cuda-graph and DP + Update FlashMLA (#21691) 3 people 2025-08-08 19:09:42 -04:00
• fe6d8257a1 [gpt-oss] Support tool call and implement MCP tool server (#22427) Chen Zhang 2025-08-08 15:06:37 -07:00
• e290594072 [Docs] Rename “Distributed inference and serving” to “Parallelism & Scaling” (#22466) Ricardo Decal 2025-08-08 12:26:21 -07:00
• f756a682d9 [gpt-oss] guard import when triton kernel is not installed (#22529) Yongye ZhuandWoosuk Kwon 2025-08-08 11:18:33 -07:00
• f0964e29cb [Benchmark] Add benchmark tool for multi turn conversations (#20267) Daniel Serebrenik 2025-08-08 20:28:50 +03:00
• e789cad6b8 [gpt-oss] triton kernel mxfp4 (#22421) Yongye Zhu 2025-08-08 08:24:07 -07:00
• e5ebeeba53 Remove exception for Python 3.8 typing from linter (#22506) Harry Mellor 2025-08-08 11:06:46 +01:00
• 7be7f3824a [Docs] Improve API docs (+small tweaks) (#22459) Harry Mellor 2025-08-08 11:02:51 +01:00
• ccdae737a0 [BugFix] Don't cancel asyncio tasks directly from destructors (#22476) Nick Hill 2025-08-08 01:13:18 -07:00
• 904063907c [Misc] fix openai version (#22485) rongfu.leng 2025-08-08 16:12:54 +08:00
• 43c4f3d77c [Misc] Begin deprecation of get_tensor_model_*_group (#22494) Cyrus Leung 2025-08-08 16:11:54 +08:00
• 1712543df6 [CI/Build] Fix multimodal tests (#22491) Cyrus Leung 2025-08-08 15:31:19 +08:00
• 808a7b69df [bench] Fix benchmark/serve.py to ignore unavailable results (#22382) lkchen 2025-08-07 23:15:50 -07:00
• 099c046463 [Doc] Sleep mode documentation (#22310) 6 people 2025-08-08 11:25:18 +07:00
• af473f0a85 [bugfix] Fix Llama3/4 issues caused by FlashInfer 0.2.10 (#22426) Po-Han Huang (NVIDIA) 2025-08-08 11:25:01 +08:00
• 157f9c1368 Fix pre-commit (#22487) Cyrus Leung 2025-08-08 11:21:54 +08:00
• 6f287915d8 Optimize MiniCPMO mask creation with vectorized implementation (#22464) ZiTian Zhao 2025-08-08 11:18:50 +08:00
• c152e2a8a0 not tie_word_embeddings for glm-4.5 and glm-4.5v (#22460) Yuxuan Zhang 2025-08-08 10:37:23 +08:00
• 17eaaef595 [Bugfix] Fix RuntimeError: Index put requires the source and destination dtypes match (#22065) Chauncey 2025-08-08 10:20:21 +08:00
• 3303f134e0 [Kernel] Add support for block FP8 on SM120 (NVIDIA 5090 and RTX PRO 6000) (#22131) Junhao Li 2025-08-07 22:18:28 -04:00
• b2c8ce57c6 Fix Flashinfer CUTLASS MOE Allgather (#21963) Shu Wang 2025-08-07 21:18:25 -05:00
• a3b9c17b56 Support Tensorrt-LLM MoE fp4 for low-latency (#21331) Shu WangandXIn Li 2025-08-07 21:18:22 -05:00
• d57dc2364e Add ModelOpt Qwen3 nvfp4 support (#20101) Zhiyu 2025-08-07 19:18:19 -07:00
• e2c8f1edec [PERF] Use pybase64 to more quickly decode prompt embeddings (#22469) Andrew Sansom 2025-08-07 21:15:32 -05:00
• 1ee5ead5f8 [ROCm] [V1] [SpecDec] Enable Speculative Decoding on ROCm V1 Engine (#21496) TJian 2025-08-07 19:13:17 -07:00
• acf8aeb79e [Misc] normalize multiprocessing Queue usage (#22371) Ning Xie 2025-08-08 09:57:27 +08:00
• 7e3a8dc906 Remove from_dict from SpeculativeConfig (#22451) Harry Mellor 2025-08-07 18:13:04 +01:00
• 139d155781 [Frontend] Use engine argument to control MM cache size (#22441) Cyrus Leung 2025-08-08 00:47:10 +08:00
• 8c9da6be22 [Core] Simplify mm processing cache (#22457) Cyrus Leung 2025-08-08 00:47:07 +08:00
• 399d2a10e2 Fix pre-commit error in main (#22462) Woosuk Kwon 2025-08-07 08:54:39 -07:00
• 4815b00f54 [gpt-oss] Generate ResponseOutputItem from Harmony Message (#22410) Chen Zhang 2025-08-07 08:33:25 -07:00
• 4da8bf20d0 [Tool] Fix auto tool call (#22434) Chen Zhang 2025-08-07 07:03:38 -07:00
• 7e0b121812 [Bugfix] Add missing packed_modules_mapping to DeepseekV2ForCausalLM (#22352) fxmarty-amd 2025-08-07 15:30:48 +02:00
• 766bc8162c [Core] Store only the keys for multi-modal data in P0 (#22198) Cyrus Leung 2025-08-07 16:45:04 +08:00
• 289b18e670 [Docs] Update features/disagg_prefill, add v1 examples and development (#22165) WeiQing Chen 2025-08-07 15:59:23 +08:00
• 35171b1172 [Doc] update docs for nightly benchmarks (#12022) Andrew Chan 2025-08-07 00:29:45 -07:00
• a2c6696bfe [Docs] Factor out troubleshooting to its own guide; add section for Ray Observability (#21578) Ricardo Decal 2025-08-07 00:29:13 -07:00
• 5e8398805e [Doc] Fix link to prefix caching design (#22384) Yong Hoon Shin 2025-08-07 00:28:15 -07:00
• 136825de75 [Misc] Enhance code formatting in mxfp4.py (#22423) Woosuk Kwon 2025-08-07 00:26:24 -07:00
• c2dba2dba8 Add H20-3e fused MoE kernel tuning configs for GLM-4.5 (#22433) JaceyShaoandshaojunqi 2025-08-07 15:24:47 +08:00
• 434d2f3f7a [Docs] Add missing dependency for docs build (#22435) Harry Mellor 2025-08-07 08:22:07 +01:00
• 8e8e0b6af1 feat: Add --enable-log-outputs flag for logging model generations (#20707) Adrián García García 2025-08-07 10:10:13 +04:00
• 82216dc21f [Misc] Support routing logic simulation (#21990) 3 people 2025-08-06 23:06:20 -07:00