Commit Graph - vLLM - iHore Software Repository

iHore/vLLM

Fork 0

263c38d74d [CI/Build] Update batch invariant test trigger (#30080) Zhewen Li 2025-12-04 16:42:37 -08:00
bcf43ab1f3 [CI/Build][AMD] Add Llama4 Maverick FP8 to AMD CI (#28695) Zhewen Li 2025-12-04 16:07:20 -08:00
4470ee2f90 [Perf] Enable separate shared_experts stream only for CUDA (#30085) Alexander Matveev 2025-12-04 19:03:17 -05:00
690cc3ef20 docs: update metrics design doc to use new vllm:kv_cache_usage_perc (#30041) TimWang 2025-12-05 07:37:14 +08:00
1f0d184590 [aot_compile]change VLLM backend to read fake args from example_value (#29104) Laith Sakka 2025-12-04 14:33:45 -08:00
c8ab988b15 [BugFix] Fix DBO assert assert B_block_table == B_q (#29933) Lucas Wilkinson 2025-12-04 14:48:54 -05:00
48a5fff66e [Bugfix] Missing tokens in return_token_ids when tool parsers is enabled in streaming mode (#29074) Peng-YM 2025-12-05 03:09:39 +08:00
1119f6e47a Abstract eplb algo (#26471)
Mercykid-bash Che Ruan mengxingkongzhouhan Harry Mellor
2025-12-05 03:09:09 +08:00
e10c84e06a Access partial_rotary_factor from rope_parameters (#29966) Harry Mellor 2025-12-04 18:42:49 +00:00
ece2825a29 [KVConnector] Remove v0-related kv connector components such as kv pipe and kv lookup buffer (#29705) Kuntai Du 2025-12-05 02:20:48 +08:00
652ba93da3 [Bugfix] Fix FP8 MoE LoRA (#29890) Jee Jee Li 2025-12-05 02:17:49 +08:00
6dcb07f676 support qwen3-vl handle requests with embeddings (#30037) Tao YunandCyrus Leung 2025-12-05 01:34:06 +08:00
46cbbca05c [CI][DCP][Perf] reduce DCP CI execution time (#29858) Qiu 2025-12-05 01:28:21 +08:00
b286a311c2 [Chore] Deprecate merge_by_field_config arg (#30035) Cyrus Leung 2025-12-05 01:21:24 +08:00
990f806473 [Doc] clarify nightly builds in developer docs (#30019) Shengqi Chen 2025-12-05 00:28:37 +08:00
5b4b42c0b6 Mark DBO test as flaky on b200 for Distributed B200 test (#29913) Doug Smith 2025-12-04 10:38:03 -05:00
cc050558f4 [Model Runner V2] Implement get_num_sampled_and_rejected kernel (#30029) Woosuk Kwon 2025-12-04 07:19:42 -08:00
5c32a06a04 Use Transformers v5 RoPE standardisation and validation (#30046) Harry Mellor 2025-12-04 14:54:28 +00:00
dd97e047e0 Fix broken multiline assert in LoRAModelManager.register_module (#30032) Yongtao Huang 2025-12-04 22:04:42 +08:00
9998ea5b57 Delete HF version of Phi 4 MM (#30049) Harry Mellor 2025-12-04 13:44:50 +00:00
74c4d80c6c [Model][6/N] Improve all pooling task | Support chunked prefill with ALL pooling (#27145) wang.yuqiandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-12-04 21:44:15 +08:00
1b7c7f5159 [release] install regex (#30008) Kevin H. Luuandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-12-04 03:18:29 -08:00
6796ce8bdb [Bugfix] Fix the issue with interleaved thinking when using streaming (#30033) ChaunceyandCyrus Leung 2025-12-04 19:11:59 +08:00
e96a6a6dca [ROCm][CI][Bugfix] Fixing the Multi-Modal Models Test (Extended) 1 group (#30013) Andreas Karatzas 2025-12-04 05:00:16 -06:00
6366c098d7 Validating Runai Model Streamer Integration with S3 Object Storage (#29320) Noa Neria 2025-12-04 12:04:43 +02:00
842aba501d [P/D] Introduce Mooncake Transfer Engine as kv_connector (#24718) dtcandNicolò Lucchesi 2025-12-04 17:51:36 +08:00
f2f4cea6cc [CI/Build][AMD] Skip test on test_hybrid_attention_mamba_tensor_shapes on ROCm, requires FLASHINFER (#29995) rasmithandRandall Smith 2025-12-04 03:30:22 -06:00
dfdda96747 [Core] Remove forced None assignment for deprecated PassConfig flags (#29994) Arpit KhandelwalandCyrus Leung 2025-12-04 04:15:04 -05:00
ffdd18111b Add DeepSeek-V3.2 tool parser. (#29848) Xu Wenqing 2025-12-04 16:46:34 +08:00
b8a6ae4158 [ROCm] add fallback for aiter fp8 decode mla (#30005) Ye (Charlotte) Qi 2025-12-04 00:45:57 -08:00
899e2ef558 [Core] Fix standalone runs of test_reset_prefix_cache_e2e (#29899) Mark McLoughlin 2025-12-04 08:22:03 +00:00
68eb5c8d97 [Misc] Move functions into PoolingMetadata (#30027) Cyrus Leung 2025-12-04 16:21:19 +08:00
5430e110c0 [CI][AMD] Match Main CI Behavior By Skipping test_eplb_spec_decode In AMD CI (#30006) Micah Williamson 2025-12-04 02:20:54 -06:00
3f1b03739a [ROCm] [Bugfix] compute_attn_mask_seqlen for qwen3 omni (#29974) TJian 2025-12-04 16:20:24 +08:00
9aa33a74b0 [Rocm][CI] Fix test_speculator_eagle3 by skipping the CompressedTensorw4a16 Model (#30001) Charlie FuandAlexei-V-Ivanov-AMD 2025-12-04 01:52:28 -06:00
fd68e909db [docs] Remove _total from counter metrics names (#30028) CYJiang 2025-12-04 15:46:15 +08:00
404fc4bfc0 [Frontend] refactor harmony utils output message parsing (#29820) daniel-salib 2025-12-03 23:36:57 -08:00
82a64b3d8f [Bugfix] fixed deepseekv32 tool calling error (#30025) ChaunceyandCyrus Leung 2025-12-04 15:12:12 +08:00
9ae2f60374 [Misc] Various cleanups for MM input processing (#29970) Cyrus Leung 2025-12-04 14:22:20 +08:00
80f8af4b2f Fix error while downloading dependencies for CPU backend (#29797) Jianwei Mao 2025-12-04 14:04:44 +08:00
8aaa81b35f [KVConnector] remove unused code (the model aware kv ops class) (#29709) Kuntai Du 2025-12-04 14:00:52 +08:00
fca3f46658 [Frontend] Fixes anthropic /v1/messages streaming not containing input_tokens on first chunk (#29971) Benjamin Bartels 2025-12-04 05:50:27 +00:00
28097d5638 [Bugfix][CPU] Fix CPU KV cache fallback memory allocation (#29604) gausah01andLi, Jiang <jiang1.li@intel.com> 2025-12-04 05:01:15 +00:00
dd38ba3a26 [Bugfix] Fix adapter_enabled IMA (#29977) Jee Jee Li 2025-12-04 12:51:15 +08:00
5f91cdda75 [Misc] Add docker build env for Ascend NPU (#30015) Li Wang 2025-12-04 11:53:00 +08:00
33a3d6c798 fix LoRA-related examples (#29956) Iceber Gu 2025-12-04 11:48:30 +08:00
c493b9d092 [CI/Build] Add MM code path to Examples Test (#29986) Zhewen Li 2025-12-03 19:21:45 -08:00
ad32e3e19c enable multi-node in external launcher mode (#29833) Xieyang Xu 2025-12-03 17:02:02 -08:00
1109f98288 [CI] fix docker image build by specifying merge-base commit id when downloading pre-compiled wheels (#29930) Shengqi Chen 2025-12-04 06:08:19 +08:00
b5407869c8 [Bugfix] Respect VLLM_CONFIGURE_LOGGING value (#28671)
Elizabeth Thomas Harry Mellor bruceszchen Roger Wang Jane Xu Nick Hill Johnny Yang
2025-12-03 16:00:52 -06:00
2902c34826 [Kernels] Remove BatchedTritonOrDeepGemmExperts and default fallback to Triton (#29929) bnellnmandTyler Michael Smith 2025-12-03 15:49:00 -05:00
ac1886588f [CI] Fix re import error (#29973) Wentao Ye 2025-12-03 15:16:54 -05:00
2fc5d6e0d7 Fix LLMEngine.del dp_group cleanup condition (#29954) Yongtao Huang 2025-12-04 04:14:44 +08:00
afe9eb408e [Bugfix] Fix flashinfer ar+norm kernel not available issue (#29960) elvischenv 2025-12-04 02:50:53 +08:00
19bee6d12d [Performance][DP/EP] Add silu_mul_per_token_group_quant_fp8_colmajor kernel (#29470)
Varun Sundar Rabindranath Varun Sundar Rabindranath Tyler Michael Smith
2025-12-03 13:04:59 -05:00
dd5d1ef780 [Bugfix] Mistral tool parser streaming update (#19425)
avigny Jeff Cook sfbemerk Chauncey Cyrus Leung
2025-12-03 18:45:31 +01:00
d1f7392c5f [ROCm][CI] Fix v1/logits_processors failure on ROCm (#29927) Micah Williamson 2025-12-03 11:17:07 -06:00
9ae3c55b10 SigLIP example add chat_template (#29902) Yu Jiaqi 2025-12-04 00:12:58 +08:00
9bcf92295a [Core] Add xxHash as a high-performance hash option for accelerating prefix caching (#29163) Lumis ChenandRussell Bryant 2025-12-04 00:06:57 +08:00
5aa9b09040 [CI/Build][AMD] Skip test_shared_storage_connector_hashes in test_shared_storage_connector.py due to hipErrorLaunchFailure when calling .cpu() (#29839) rasmithandRandall Smith 2025-12-03 08:56:35 -06:00
1bb17ecb39 [CPU Backend] [Doc]: Update Installation Docs for CPUs (#29868) ioana ghiban 2025-12-03 14:33:50 +01:00
15b1511a15 [GPU Backend] [Doc]: Remove duplicate statements on missing GPU wheels. (#29962) ioana ghiban 2025-12-03 13:56:47 +01:00
b78772c433 [Frontend] supports deepseekv32 chat template (#29837) Chauncey 2025-12-03 20:53:44 +08:00
f5d3d93c40 [docker] Build CUDA kernels in separate Docker stage for faster rebuilds (#29452) Amr Mahdi 2025-12-03 03:41:53 -08:00
78f4bb0ba8 [DOC] Add Arm to list of compute resouces providers (#29894) Fadi Arafeh 2025-12-03 11:36:58 +00:00
b294e28db2 [refactor] CTMoEMethods to use QuantizationArgs (#28871) HDCharlesandIsotr0py 2025-12-03 06:00:56 -05:00
787b84a9fc [Bugfix] Follow-up fix on MediaWithBytes (#29951) Roger Wang 2025-12-03 02:42:49 -08:00
42c1949643 [Bugfix][Quantization] Support BF16 tensors on GGUF (#29948) Tsukasa OI 2025-12-03 19:33:46 +09:00
cc4e296ea6 [CI/Build] Avoid duplicate empty inputs test for common multimodal generation tests (#29907) Isotr0py 2025-12-03 18:27:36 +08:00
a21cd9ed23 [Bugfix] Fix incorrect image_grid_thw rank for HunyuanOCR from missing merge_by_field_config=True (#29950) Isotr0py 2025-12-03 18:05:10 +08:00
7fe9c1a223 [CI] Add Async Eplb nightly CI tests (#29385) WeiQing ChenandCyrus Leung 2025-12-03 17:51:08 +08:00
3f42b05fbc [Refactor] [1/N] to simplify the vLLM serving architecture (#28040) Chauncey 2025-12-03 17:26:39 +08:00
69520bc695 Add logging for cudagraph related info (#29825) Yong Hoon Shin 2025-12-02 23:01:48 -10:00
3a7751485b [responsesAPI] support input output messages for non harmony models (#29549) Andrew XiaandAndrew Xia 2025-12-02 23:59:23 -08:00
bbfb55c29e [Misc] Allow fetch_* utils to access local files by default (#29932) Cyrus Leung 2025-12-03 15:49:34 +08:00
0bec63fa31 [BugFix] fix imgs_pos in hunyuan_vl (#29879) JackieWuandIsotr0py 2025-12-03 14:20:37 +08:00
c719c40540 [Bugfix] Defunctionalize TRTLLM AR+Norm op for avoiding extra clone kernel before it (#29631) elvischenvandLuka Govedič 2025-12-03 13:15:50 +08:00
b08025a83b [Docs] Discuss api key limitations in security guide (#29922) Russell Bryant 2025-12-02 23:57:28 -05:00
d7284a2604 [Core] Rename PassConfig flags as per RFC #27995 (#29646) Arpit KhandelwalandLuka Govedič 2025-12-02 22:38:55 -05:00
506ed87e87 [ROCm][CI][Bugfix] Disable Flash/MemEfficient SDP on ROCm to avoid HF Transformers accuracy issues (#29909) Andreas Karatzas 2025-12-02 20:36:49 -06:00
4dd7978374 [Bugfix] Fix regression on pooling models from PR#29621 (#29921) Roger Wangandgemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> 2025-12-02 18:33:45 -08:00
5cdd664509 [BugFix] Fix assert in build_for_cudagraph_capture (#29893) Lucas Wilkinson 2025-12-02 19:56:54 -05:00
5f67361fd1 Reverting re-direction to amd_mi355_X. (#29914) Alexei-V-Ivanov-AMD 2025-12-02 18:40:02 -06:00
5d91d2b292 [Doc] Add allocate_slots parameter docs (#29777) maang-handChen Zhang 2025-12-03 07:23:09 +08:00
c014de1ec7 [ROCm][CI] Fix test_cudagraph_mode.py Failure For AMD CI (#29808) Micah Williamson 2025-12-02 16:54:36 -06:00
1b1e35aaf9 [BUGFIX] Fix regex pattern for Mistral Tool Call (#29918) Julien Denize 2025-12-02 23:51:58 +01:00
5e5646e206 [BUGFIX] llama_4_scaling wrongly passed to DeepseekAttention (#29908) Julien Denize 2025-12-02 23:51:20 +01:00
0a9caca9f5 [Bugfix] fix --scheduling-policy=priority & n>1 crashes engine (#29764) ChaunceyandNick Hill 2025-12-03 06:42:28 +08:00
e6f114ac25 [Bugfix][EPLB] Prevent user-provided EPLB config from being overwritten with defaults (#29911) Sage Moore 2025-12-02 14:20:22 -08:00
6fc5841db1 Fix some more Transformers nightly tests (#29872) Harry Mellor 2025-12-02 21:49:44 +00:00
3ff5b53bc2 Bump actions/setup-python from 6.0.0 to 6.1.0 (#29768) dependabot[bot]anddependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> 2025-12-02 21:29:32 +00:00
1528e079e2 [Perf] Avoid pageable HtoD transfer in MinTokensLogitsProcessor (#29826) jthomson04 2025-12-02 13:25:52 -08:00
afb1e5b380 [CI][ROCm][tests/v1/e2e] Fix multiprocessing launch for the test (#29123) Divakar Verma 2025-12-02 14:46:10 -06:00
1c593e117d Fix boolean nested params, add dict format support, and enhance plotting for vllm bench sweep (#29025)
Copilotcopilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>ProExpertProg Luka Govedič Luka Govedič
2025-12-02 20:40:56 +00:00
a2b053dc85 feat(model): Add BitsAndBytes quantization support for Qwen3-Omni-MoE (#29896) Navanit Dubey 2025-12-03 00:58:35 +05:30
1d93f11675 [Attention][CUDAGraph] Remove CG padding from attention backends (#29352) Matthew Bonanni 2025-12-02 13:48:08 -05:00
2d613de9ae [CI/Build] Fixes missing runtime dependencies (#29822) Benjamin Bartels 2025-12-02 18:21:49 +00:00
c77b9929a0 Update AMD-CI testing mirror (as of 2025-12-02) (#29898) Alexei-V-Ivanov-AMD 2025-12-02 11:52:54 -06:00
63b1da76ba [Chore]: Reorganize gguf utils funtions under transformers_utils (#29891) Isotr0py 2025-12-03 01:33:23 +08:00
52cb349fc0 [responsesAPI][3] ResponsesParser to set up non harmony MCP (#29413) Andrew XiaandAndrew Xia 2025-12-02 08:24:45 -08:00

... 113 114 115 116 117 ...

Commit Graph Select branches Hide Pull Requests main patches sm86 Mono Color

Commit Graph

Select branches

Hide Pull Requests

main

patches

sm86