Commit Graph
8528 Commits
Author SHA1 Message Date
danielafrimi 6ec0d8dbe4 [Fix]Load kv-cache dtype from hf_quant_config.json automatically (#29980)
Signed-off-by: Daniel Afrimi <dafrimi@nvidia.com>
2025-12-12 11:27:47 -08:00
Xin Yang 1f19d8f899 [Perf] Set split_k to 1 for triton_kernels (#30528)
Signed-off-by: Xin Yang <xyangx@amazon.com>
2025-12-12 14:07:57 -05:00
shivampr cd7740ac5c [ROCm] Enable Triton ScaledMM fallback + kernel selection fix (#26668)
Signed-off-by: Shivam <shivampr.dev@gmail.com>
Signed-off-by: Shivam <shivamprasad91@gmail.com>
2025-12-12 13:28:20 -05:00
Wentao Ye 02a5880394 [CI] Fix mypy for vllm/v1/executor (#30517)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-12-12 18:05:34 +00:00
realliujiaxu d2c919dcc2 [bugfix] fix bug when top_logprobs=0 with spec decoding (#30059)
Signed-off-by: realliujiaxu <realliujiaxu@163.com>
2025-12-12 09:03:35 -08:00
Benjamin Bartels f3237f3f6b [Frontend] Fixes anthropic streaming message_start usage nesting (#30266)
Signed-off-by: bbartels <benjamin@bartels.dev>
2025-12-12 16:28:54 +00:00
9c0ee995a8 [Kernel] Support CUDA Graphs in 3D Triton Attention Kernel (#28306)
Signed-off-by: Jan van Lunteren <jvl@zurich.ibm.com>
Signed-off-by: jvlunteren <161835099+jvlunteren@users.noreply.github.com>
Co-authored-by: Thomas Parnell <tom.parnell@gmail.com>
Co-authored-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-12-12 16:55:40 +01:00
Michael Goin 09ad3b76b3 [Bug] Fix attention_backend arg string parsing (#30534)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-12-12 08:40:50 -07:00
Christina NormanIsotr0pyIsotr0pygemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
dc13c99eed fix(gguf): Disable bfloat16 for GGUF on blackwell device (#30408)
Signed-off-by: Christina <truffle@gmail.com>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Christina Norman <christina@example.com>
Co-authored-by: Isotr0py <isotr0py@users.noreply.github.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-12-12 23:10:12 +08:00
Vladislav Nosivskoy 3e34adcdfb [DeepSeek V3.2] Proper drop_thinking logic (#30490)
Signed-off-by: Vladislav Nosivskoy <vladnosiv@gmail.com>
2025-12-12 15:01:06 +00:00
Lucas Wilkinson 3e41992fec [Attention] Use sparse prefill kernel for fp8 kv-cache in DeepSeek-v3.2 (#27532)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-12 05:57:47 -08:00
Jaehwang Jung f90319d5d1 [Bugfix] Schedule failure due to wrong get_image_size_with_most_features (#29692) 2025-12-12 02:27:20 -08:00
Ben BrowningandChauncey 8f8fda261a [Bugfix] Multiple fixes for gpt-oss Chat Completion prompting (#28729)
Signed-off-by: Ben Browning <bbrownin@redhat.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
2025-12-12 12:59:53 +08:00
Zhengxu Chen fe1787107e [compile] Parse compile range cache keys as Range during cache loading. (#30516)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
2025-12-12 04:30:51 +00:00
Nick Hill 947dfda9c2 [LMCache] Relax lmcache version requirement (#30425)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-12-11 18:18:47 -09:00
Michael GoinandHarry Mellor 9f2fc16a69 [Bugfix][Model] Fix Afmoe rope_parameters issue (#30505)
Signed-off-by: mgoin <mgoin64@gmail.com>
Signed-off-by: Michael Goin <mgoin64@gmail.com>
Co-authored-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-12 02:53:57 +00:00
Bhanu Prakash Voutharoja 6a6fc41c79 gptq marlin quantization support for fused moe with lora (#30254)
Signed-off-by: Bhanu068 <voutharoja.bhanu06@gmail.com>
2025-12-12 02:27:22 +00:00
Fadi Arafeh f355ad5412 [CPU][FIX] Fix build failures on Arm CPUs with torch nightly (#30481)
Signed-off-by: Fadi Arafeh <fadi.arafeh@arm.com>
2025-12-12 02:09:25 +00:00
Lucas Wilkinson 042da73244 [Core] Refactor _build_attention_metadata (#29628)
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
2025-12-11 17:54:12 -08:00
jiahanc 0ab23c2b2b [fix] fix SM check for Flashinfer TRTLLM MOE (#30314)
Signed-off-by: jiahanc <173873397+jiahanc@users.noreply.github.com>
2025-12-12 01:00:58 +00:00
Andrew BriandandAndrew Briand a00d88973d [EPLB] Support EPLB w/ NVFP4 (#29804)
Signed-off-by: Andrew Briand <abriand@nvidia.com>
Co-authored-by: Andrew Briand <abriand@nvidia.com>
2025-12-11 22:59:40 +00:00
c817b14151 [Perf] Optimize deepgemm experts initialization, 3.9% TTFT improvement (#30494)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: li-jinpeng <3332126450@qq.com>
Co-authored-by: youkaichao <youkaichao@gmail.com>
2025-12-11 17:28:34 -05:00
Nicolò Lucchesi 0efd9f867c [Core] Whisper Enable Encoder Batching (#29421)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-12-11 21:06:51 +00:00
Xingyu LiuandCyrus Leung 90d6cf921f [BugFix][MM]support VLLM_RANDOMIZE_DP_DUMMY_INPUTS (#30472)
Signed-off-by: Xingyu Liu <charlotteliu12x@gmail.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-12-11 21:00:15 +00:00
Harry Mellor cf3eacfe58 Standardise get_rope to use rope_parameters["partial_rotary_factor"], not rotary_dim (#30389)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 20:45:23 +00:00
Zhengxu Chen 92fea56fd1 [compile] Stop one-off setting enable_aot_compile and use context manager instead. (#30503)
Signed-off-by: zhxchen17 <zhxchen17@fb.com>
2025-12-11 20:28:03 +00:00
Andreas Karatzas 72aaac5b66 [ROCm][Bugfix] Add MLACommonMetadata to allowed attention types for speculative decoding (#30430)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2025-12-11 19:25:01 +00:00
汪志鹏 0e71eaa644 [Feature] AWQ marlin quantization support for fused moe with lora (#30442)
Signed-off-by: princepride <wangzhipeng628@gmail.com>
2025-12-11 18:03:32 +00:00
Harry Mellor 8781cd6b88 Add Eagle and Eagle3 support to Transformers modeling backend (#30340)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 17:02:10 +00:00
Julien DenizeandPatrick von Platen aa3c250c48 [IMPROVEMENT] Change MistralReasoningParser behavior (#30391)
Signed-off-by: juliendenize <julien.denize@mistral.ai>
Signed-off-by: Julien Denize <40604584+juliendenize@users.noreply.github.com>
Co-authored-by: Patrick von Platen <patrick.v.platen@gmail.com>
2025-12-11 17:53:26 +01:00
Harry Mellor 93db3256a4 Give pooling examples better names (#30488)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 16:22:58 +00:00
Harry Mellor 97a042f3bc Make the httpx logger less annoying when Transformers v5 is installed (#30480)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-12-11 15:44:56 +00:00
Cyrus Leung 3a3b06ee70 [Misc] Improve error message for is_multimodal (#30483)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-11 06:39:51 -08:00
Martin Hickey f4417f8449 [KVConnector] Add KV events to KV Connectors (#28309)
Signed-off-by: Martin Hickey <martin.hickey@ie.ibm.com>
2025-12-11 15:30:29 +01:00
QiuandCyrus Leung a11f4a81e0 [Misc][PCP&DCP] relocate PCP feature check (#30050)
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
Co-authored-by: Cyrus Leung <tlleungac@connect.ust.hk>
2025-12-11 03:36:18 -08:00
Kenichi Maehashi 853611bb18 Fix typo of endpoint name in CLI args docs (#30473)
Signed-off-by: Kenichi Maehashi <maehashi@preferred.jp>
2025-12-11 11:07:56 +00:00
wang.yuqi a5f9fb5960 [Deprecation] Deprecation --convert reward, use --convert embed instead. (#30463)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
2025-12-11 10:18:25 +00:00
jeremyteboulandJeremy Teboul 4515eb1a0b [Fix] Update lazing loading of video loader backend (#30444)
Signed-off-by: Jeremy Teboul <jeremyteboul@fb.com>
Co-authored-by: Jeremy Teboul <jeremyteboul@fb.com>
2025-12-11 10:14:57 +00:00
Cyrus Leung 13d63b65e0 [Deprecation] Remove missed fallback for embed_input_ids (#30469)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-11 10:06:36 +00:00
Rei. 6299628d32 [bugfix] fix MiniMaxM2ReasoningParser streaming output not separating reasoning_content. (#29882)
Signed-off-by: Rei <1477174254@qq.com>
2025-12-11 09:05:08 +00:00
Ming Yang fba8906930 [perf] Use direct copy (broadcast) instead of cat for k_nope/k_pe in MLA prefill (#29710)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-12-11 08:20:45 +00:00
Ning Xie d02d1043de fix: enhance human_readable_int function (#30337)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-12-10 23:30:33 -08:00
Cyrus Leung 979f50efd0 [Deprecation] Remove fallbacks for embed_input_ids and embed_multimodal (#30458)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-11 06:58:23 +00:00
gh-wf 36c9ce2554 Ensure minimum frames for GLM 4.6V compatibility (#30285)
Signed-off-by: Wayne Ferguson <wayneferguson@gmail.com>
2025-12-11 05:26:49 +00:00
Wentao Ye d6464f2679 [Chore] Fix torch precision warning (#30428)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-12-11 04:05:56 +00:00
Cyrus Leung 7e24e5d4d6 [Deprecation] Remove deprecated task, seed and MM settings (#30397)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-10 19:59:39 -08:00
Cyrus Leung 5a87d8b9b1 [Deprecation] Remove deprecated plugin and compilation fields for v0.13 release (#30396)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-12-10 19:59:35 -08:00
d1e1fb4363 [Bugfix] Fix grouped_topk pytorch impl when num_experts can't be grouped properly (#29439)
Signed-off-by: Divakar Verma <divakar.verma@amd.com>
Co-authored-by: Gregory Shtrasberg <156009573+gshtras@users.noreply.github.com>
Co-authored-by: TJian <tunjian.tan@embeddedllm.com>
2025-12-10 19:47:18 -08:00
Andreas Karatzas b51255f369 [ROCm] Fix broken import in platform attention backend dispatching (#30432)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
2025-12-11 01:12:58 +00:00
Sage Moore b4054c8ab4 Revert "[CI] Add Async Eplb nightly CI tests (#29385)" (#30431) 2025-12-11 00:48:35 +00:00