 Bugen Zhao
|
efa494e397
|
refactor setup.py to extract stuff into build_rust.py
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 22:39:17 +08:00 |
|
|
Bugen Zhao
|
74b77a593a
|
update dockerfile image
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 22:38:24 +08:00 |
|
|
Bugen Zhao
|
ec53889a3b
|
simplify to only match .so, as .dylib will also be renamed to .so under macos
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 22:13:09 +08:00 |
|
|
Bugen Zhao
|
ede3d4ddf6
|
skip tests when _rust_tool_parser is absent
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 22:12:48 +08:00 |
|
|
Bugen Zhao
|
7301a834fa
|
fix glob issue
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 22:06:14 +08:00 |
|
|
Bugen Zhao
|
7104ac6b5d
|
simplify setup.py
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 11:40:33 +00:00 |
|
|
Bugen Zhao
|
9a98eccb49
|
cover two calls case
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
2ce1e2ba71
|
do not infer finished but just leave it unhandled
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
2496f66f7f
|
Run tool parser tests before tokenizer tests
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
d18b7f2723
|
Build Rust parser extension in Docker rust stage
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
80b633f076
|
ci: configure PyO3 Python for Rust tests
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
28f589ebb1
|
do not enable pyo3 on --all-features
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:02 +00:00 |
|
|
Bugen Zhao
|
98998279d4
|
fix fmt & try import
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:01 +00:00 |
|
|
Bugen Zhao
|
71d208089e
|
add tests with deepseek v4
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:01 +00:00 |
|
|
Bugen Zhao
|
0ac6fc8352
|
Add Rust tool parser Python bridge
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 09:50:01 +00:00 |
|
|
Bugen ZhaoandGitHub
|
fdfb2566c0
|
[Rust Frontend] [CI] Unify Rust artifact builds with setuptools-rust (#44981)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-10 17:48:34 +08:00 |
|
|
Juan Pérez de AlgabaandGitHub
|
8a5cf1ccd6
|
[Security] Fix remote DoS via invalid recovered token reinjection (#44744)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-06-10 02:31:43 -07:00 |
|
|
Kunshang JiandGitHub
|
fe1d923afc
|
[BUGFIX][XPU] fix xpu flash_attn_varlen_func interface (#45110)
Signed-off-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-10 17:07:40 +08:00 |
|
|
|
32daf56b42
|
[Refactor] Rename rocm_moe.py to rocm_moe_rdna.py (#45011)
Signed-off-by: JartX <sagformas@epdcenter.es>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-10 17:02:09 +08:00 |
|
|
Andreas KaratzasandGitHub
|
82a42234be
|
[ROCm][CI] Defer AITER sampler import and isolate server test PYTHONPATH (#44823)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
|
2026-06-10 08:56:11 +00:00 |
|
|
Harry MellorandGitHub
|
af9f583344
|
Revert "[Bugfix][CI] Gemma3 Transformers multimodal encoder profiling and build prompt-embedding fixtures" (#45029)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-10 01:37:03 -07:00 |
|
|
yihengandGitHub
|
bd2d83ff31
|
[SpecDecode] Reduce TP communication for large-vocab draft models speculative decoding (#39419)
Signed-off-by: EanWang211123 <wangyiheng@sangfor.com.cn>
|
2026-06-10 07:59:24 +00:00 |
|
|
xiaohuguo2023andGitHub
|
bb78168b21
|
[ROCm][gpt-oss] Hybrid CDNA4 swizzle gate for A8W4 MoE (#44804)
Signed-off-by: Xiaohu Guo <Xiaohu.Guo@amd.com>
|
2026-06-09 23:59:44 -07:00 |
|
|
|
89c6a41001
|
[Bench] Add BFCL dataset for vllm bench serve tool-calling workloads (#42457)
Signed-off-by: Li Zhang <lzhanga@amazon.com>
Co-authored-by: Li Zhang <lzhanga@amazon.com>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Chauncey <chaunceyjiang@gmail.com>
|
2026-06-09 23:59:18 -07:00 |
|
|
|
7fdfa6441d
|
Model/colbert autoweightsloader (#44999)
Signed-off-by: Furkan Fidan <dev@yufufi.com>
Co-authored-by: wang.yuqi <yuqi.wang@daocloud.io>
|
2026-06-09 23:58:50 -07:00 |
|
|
Harry MellorandGitHub
|
e9b728de8a
|
Change from owning configs to owning config utils (#45058)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
|
2026-06-10 06:40:25 +00:00 |
|
|
|
5828a205ef
|
Fix Harmony tool descriptions for optional fields (#44686)
Signed-off-by: Varun Shenoy <varun.vinayak.shenoy@oracle.com>
Co-authored-by: Codex <codex@openai.com>
|
2026-06-09 23:29:22 -07:00 |
|
|
Yaoming ZhanandGitHub
|
7a74f31d2e
|
[Rust Frontend] Add seed_oss and step3p5 reasoning parsers (#44552)
Signed-off-by: yzhan1 <zhanyaoming2014@gmail.com>
|
2026-06-09 23:01:33 -07:00 |
|
|
|
47930b59ca
|
[Bugfix] Handle HWC images in ImageProcessorItems.get_image_size (#45057)
Signed-off-by: YellowFoxH4XOR <yellowfoxh4xor@gmail.com>
Co-authored-by: Claude <noreply@anthropic.com>
|
2026-06-10 05:35:50 +00:00 |
|
|
Flora FengandGitHub
|
6aec99f030
|
[Refactor] Remove dead states from chat completion serving (#45081)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-09 22:20:15 -07:00 |
|
|
bnellnmandGitHub
|
f4966f8b3d
|
[Bugfix] Fix weight loading issues caused by #41184 (#45054)
Signed-off-by: Bill Nell <bnell@redhat.com>
|
2026-06-10 01:20:13 -04:00 |
|
|
Mohammad Miadh AngkadandGitHub
|
2c9c07c85e
|
[Bugfix][CI/Build] Fix Rust frontend build after chat conversion refactor (#45085)
Signed-off-by: Mohammad Miadh Angkad <176301910+mmangkad@users.noreply.github.com>
|
2026-06-09 20:04:41 -07:00 |
|
|
Change72andGitHub
|
320c52b134
|
[Bench] benchmark_serving_multi_turn: make non-standard conversation_id payload opt-in (#43756)
Signed-off-by: Change72 <cguo51@asu.edu>
|
2026-06-09 19:41:56 -07:00 |
|
|
|
6deb05e0e4
|
[Core][Model] Gemma4: Unified FA4 for all layers + FlashAttention mm_prefix support (#42175)
Signed-off-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Luciano Martins <lucianommartins@users.noreply.github.com>
Co-authored-by: Lucas Wilkinson <lwilkins@redhat.com>
Co-authored-by: Matthew Bonanni <mbonanni@redhat.com>
|
2026-06-09 17:45:39 -07:00 |
|
|
Flora FengandGitHub
|
d82ac00923
|
[Refactor][Mistral] Extract parsing logic into MistralParser (#44596)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
|
2026-06-10 00:12:23 +00:00 |
|
|
Bugen ZhaoandGitHub
|
dac9e9a640
|
[Rust Frontend] Extract shared options in route helper params (#44884)
Signed-off-by: Bugen Zhao <i@bugenzhao.com>
|
2026-06-09 17:02:35 -07:00 |
|
|
Wentao YeandGitHub
|
d7607ad273
|
[Bug] Fix deepseek v4 OOM issue (#44914)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
|
2026-06-09 15:47:06 -07:00 |
|
|
|
d955745d58
|
[ROCm][CI] fix test_rope_kvcache_fusion.py (#44678)
Signed-off-by: charlifu <charlifu@amd.com>
Co-authored-by: Rohan Potdar <66227218+Rohan138@users.noreply.github.com>
|
2026-06-09 21:53:46 +00:00 |
|
|
Micah WilliamsonandGitHub
|
e1ed89dbee
|
Revert "[Kernel] Speed up silu_and_mul_per_block_quant with warp-shuf… (#45066)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-09 14:12:06 -07:00 |
|
|
|
1c2ffc6f88
|
feat(multi-turn-bench): add api_key and custom headers for multi turn benchmark (#44516)
Signed-off-by: Jimmy <jinmingyi1998@sina.cn>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
Co-authored-by: simon-mo <simon.mo@hey.com>
|
2026-06-09 14:00:07 -07:00 |
|
|
Jiangyun ZhuandGitHub
|
ca4cfd8731
|
[Bugfix] fix qwen3.5 ep weight loading (#45002)
Signed-off-by: zjy0516 <riverclouds.zhu@qq.com>
|
2026-06-09 13:55:30 -07:00 |
|
|
Micah WilliamsonandGitHub
|
c9c1540e61
|
[ROCm][V2] Fix failed assertion in Llama models when using EAGLE with ROCM_AITER_FA (#44936)
Signed-off-by: Micah Williamson <micah.williamson@amd.com>
|
2026-06-09 13:30:52 -05:00 |
|
|
|
c1d754d681
|
[Mooncake] Use all HCAs on multi-NIC hosts instead of GPU-indexed RNIC selection (#43799)
Signed-off-by: Dao Le <Dao007forever@gmail.com>
Co-authored-by: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
|
2026-06-09 11:05:36 -07:00 |
|
|
|
01d8cd92dd
|
[ROCm][Perf] Use fused softplus-sqrt-topk router under AITER fused-MoE (#44945)
Co-authored-by: vLLM Contributor <contributor@vllm.ai>
|
2026-06-09 17:53:05 +00:00 |
|
|
|
a4b14b98c6
|
[Kernel] Speed up silu_and_mul_per_block_quant with warp-shuffle reduction + vectorized I/O (#44173)
Signed-off-by: SII-yangdian <yangdian@sii.edu.cn>
Co-authored-by: SII-yangdian <yangdian@sii.edu.cn>
|
2026-06-09 10:41:26 -07:00 |
|
|
Juan Pérez de AlgabaandGitHub
|
cf1c906724
|
[Security] Fix image EXIF orientation and tRNS transparency handling (#44974)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-06-09 09:34:44 -07:00 |
|
|
|
766ce2bb6b
|
Fix MiDashengLM TP>1 crash in audio encoder attention (#44408)
Signed-off-by: Michał Ganczarenko <michal.ganczarenko@intel.com>
Co-authored-by: Kunshang Ji <kunshang.ji@intel.com>
|
2026-06-09 09:29:14 -07:00 |
|
|
|
3d119f78f7
|
[Docs] Add KV offloading usage guide (single- and multi-tier) (#44415)
Signed-off-by: Ronen Schaffer <ronen.schaffer@ibm.com>
Co-authored-by: mergify[bot] <37929162+mergify[bot]@users.noreply.github.com>
|
2026-06-09 19:20:23 +03:00 |
|
|
Juan Pérez de AlgabaandGitHub
|
1b1359c332
|
[Security] Fix DoS via audio decompression bomb in speech-to-text endpoint (#44970)
Signed-off-by: jperezde <jperezde@redhat.com>
|
2026-06-10 00:18:53 +08:00 |
|
|
Tyko NiemiandGitHub
|
cad4ca12b8
|
[Bugfix] Add X-Session-ID from conversation_id in multi-turn benchmark (#44663)
Signed-off-by: Tyko Niemi <tyko.niemi@amd.com>
|
2026-06-09 08:57:00 -07:00 |
|