8299 Commits

Author SHA1 Message Date
Michael Goin
c494f96fbc
Use UV_LINK_MODE=copy in Dockerfile to avoid hardlink fail (#22128)
Signed-off-by: mgoin <mgoin64@gmail.com>
2025-08-05 06:57:10 -07:00
Nicolò Lucchesi
0c275ad5ad
[V0 Deprecation][TPU] Remove V1 flag check from tests (#22248)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-08-05 06:53:23 -07:00
Ning Xie
74333ae2f6
[Misc] correct static type check for GroupCoordinator (#21946)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-08-05 03:17:46 -07:00
elvischenv
83156c7b89
[NVIDIA] Support Flashinfer TRT-LLM Prefill Attention Kernel (#22095)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
2025-08-05 02:45:34 -07:00
Wentao Ye
4771df7b2b
[Feature] Non-contiguous Support for FP8 Quantization (#21961)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-08-05 02:36:43 -07:00
Benji Beck
05fae02175
Migrate KimiVLImagePixelInputs to TensorSchema (#21769)
Signed-off-by: Benji Beck <benjibeck@meta.com>
Co-authored-by: Isotr0py <2037008807@qq.com>
2025-08-05 02:36:18 -07:00
Nicolò Lucchesi
d1bf1b9711
[Docs][TPU] Highlight TPU Software version selection (#22242)
Signed-off-by: NickLucche <nlucches@redhat.com>
2025-08-05 02:33:46 -07:00
wang.yuqi
586f286789
[Model] Pooling model activation supports per request control by PoolingParams (#20538)
Signed-off-by: wang.yuqi <noooop@126.com>
2025-08-05 00:37:00 -07:00
Cyrus Leung
811ac13d03
[Core] Factor out common logic for MM budget calculation (#22228)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-04 23:54:55 -07:00
Michael Goin
e79a12fc3a
[UX] Fail if an invalid attention backend is specified (#22217)
Signed-off-by: mgoin <michael@neuralmagic.com>
2025-08-04 23:54:52 -07:00
Cyrus Leung
cdfd6871a5
[Bugfix] Misaligned params in TreeAttentionImpl (#22226)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-04 22:40:09 -07:00
ZiTian.Zhao
4b3e4474d7
Optimize configuration access with LRU cache in custom ops (#22204)
Signed-off-by: zitian zhao <zitian.zhao@tencentmusic.com>
2025-08-04 21:43:24 -07:00
Ning Xie
bd3db7f469
[Misc] log more detailed message for ensure_model_parallel_initialized (#22144)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-08-04 19:36:55 -07:00
Ning Xie
29b97c0995
[Doc] add backend to doc string of initialize_model_parallel (#22142)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-08-04 19:36:20 -07:00
elvischenv
7b455cf1c0
[Misc] Remove pass_config from CompilationConfig dump_json excluded (#21911)
Signed-off-by: elvischenv <219235043+elvischenv@users.noreply.github.com>
2025-08-04 19:17:18 -07:00
tlipoca9
8a6e108e76
fix: kimi_k2 return empty tool call list (#22149)
Signed-off-by: tlipoca9 <tlipoca9@gmail.com>
2025-08-04 19:15:31 -07:00
Wentao Ye
d7b28f3415
[Log] DeepGEMM Update Log for Unaligned Problem Size (#22208)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-08-04 19:13:19 -07:00
Yuxuan Zhang
6fa41e0c32
self.gate dtype update for GLM-4.5 (#22203)
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
2025-08-04 19:12:38 -07:00
Gregory Shtrasberg
031ca762d7
[ROCm][Bugfix] Compilation passes fix (#22202)
Signed-off-by: Gregory Shtrasberg <Gregory.Shtrasberg@amd.com>
2025-08-04 19:12:28 -07:00
TJian
6ad6b8e115
[FEAT] Refactor ROPE into module (#22192)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
2025-08-04 19:12:16 -07:00
lkchen
f4f4e7ef27
[V0 deprecation][P/D] Deprecate v0 KVConnectorBase code (1/2) (#21785)
Signed-off-by: Linkun Chen <github@lkchen.net>
2025-08-04 19:11:33 -07:00
Giancarlo Delfin
5ea71ff46f
[V1] reduce block size for tree attention correctness test to fix 'ou… (#22207)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
2025-08-04 19:11:06 -07:00
Woosuk Kwon
7175817637
Revert "[Bugfix] V1 Fix the cursor leakage issue during request scheduling." (#22223) 2025-08-04 18:37:06 -07:00
PiteXChen
2dffac464c
[Bugfix] V1 Fix the cursor leakage issue during request scheduling. (#21173)
Signed-off-by: CLFutureX <775523362@qq.com>
2025-08-04 18:34:10 -07:00
Po-Han Huang (NVIDIA)
bdcb42e45d
[NVIDIA] Auto detect modelopt quant and fix DSR1-FP4 weight loading (#22073) 2025-08-04 21:02:55 -04:00
Zhonghua Deng
c09efff976
[Bugfix][V1][P/D]Fix the uneven polling issue in the toy proxy for P2pNcclConnector (#21819)
Signed-off-by: Abatom <abzhonghua@gmail.com>
2025-08-04 20:17:05 +00:00
ericehanley
309c1bb822
[Bug] Update auto_tune.sh to separate benchmarking and profiling. (#21629)
Signed-off-by: Eric Hanley <ericehanley@google.com>
2025-08-04 15:12:06 +00:00
Woosuk Kwon
9af654cc38
[Responses API] Ignore store=True and process the request by default (#22185)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-04 05:12:48 -07:00
Raghav Ravishankar
a5fff3bd49
Fix Arcee model weight loading: Add custom load_weights (#21725)
Signed-off-by: alyosha-swamy <raghav@arcee.ai>
2025-08-04 04:09:56 -07:00
Cyrus Leung
1539ced93a
[Doc] Update pooling model docs (#22186)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-08-04 03:37:06 -07:00
22quinn
54de71d0df
[Sampler] Support returning all logprobs or logits (#21792)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-08-04 03:04:12 -07:00
Isotr0py
fed5849d3f
[Bugfix] Fix failing GGUF models test (#22174)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-08-04 01:27:02 -07:00
Weixiao Huang
c1b4eb048a
[feat] move WEIGHT_SCALE_SUPPORTED into raise block to accelerate RLHF weight loading (#21164)
Signed-off-by: huangweixiao <huangweixiao@msh.team>
2025-08-04 15:43:06 +08:00
Jee Jee Li
a7b8788d2c
[Misc] Modify the organization of GLM series (#22171)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-08-03 23:51:20 -07:00
Tyler Michael Smith
8ecb3e9e93
[CI Bugfix] Fix wNa16 kernel not found for test_shared_storage_connector_hashes (#22163)
Signed-off-by: Tyler Michael Smith <tyler@neuralmagic.com>
2025-08-03 22:19:04 -07:00
Chenxi Yang
e5949e5ae0
Remove index_put from MM embeddings merging (#22105)
Co-authored-by: Chenxi Yang <cxyang@meta.com>
2025-08-03 22:15:14 -07:00
ZiTian.Zhao
49bcd893e7
[refactor] improve ConstantList exception specificity (#22156)
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
2025-08-03 22:14:49 -07:00
Giancarlo Delfin
aa7012eb6d
Add tree attention backend for v1 (part 1) (#20401)
Signed-off-by: Giancarlo Delfin <gdelfin@meta.com>
2025-08-03 22:13:26 -07:00
Ning Xie
c2e75b3c11
remove duplicate code within cleanup_dist_env_and_memory (#22147)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-08-03 20:03:58 -07:00
Abirdcfly
0d7db16a92
[PD] add test for chat completions endpoint (#21925)
Signed-off-by: Abirdcfly <fp544037857@gmail.com>
2025-08-03 19:57:03 -07:00
22quinn
845420ac2c
[RLHF] Fix torch.dtype not serializable in example (#22158)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-08-04 02:43:33 +00:00
ZiTian.Zhao
e27d25a0dc
[fix] fix correct assertion syntax error in attention utils. (#22154)
Signed-off-by: zitian.zhao <zitian.zhao@tencentmusic.com>
2025-08-03 19:24:02 -07:00
Seiji Eicher
6f5478298d
Use aiohttp connection pool for benchmarking (#21981)
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
2025-08-03 19:23:32 -07:00
Isotr0py
6a39ba85fe
[Bugfix] Fix failing multimodal standard test (#22153)
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
2025-08-03 19:04:38 +00:00
Yuxuan Zhang
d3c18c9cb0
fuse fp32 for GLM-4.5 e_score_correction_bias (#22143)
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
2025-08-03 09:04:54 -07:00
TankNee
83f7bbb318
Add chat doc in quick start (#21213)
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-08-03 07:47:55 -07:00
Li, Jiang
b5dfb94fa0
[CI/Build][Bugfix] Fix Qwen2.5 tests in CPU CI via fallback silu_and_mul to torch native implementation (#22145)
Signed-off-by: jiang1.li <jiang1.li@intel.com>
2025-08-03 05:34:04 -07:00
Woosuk Kwon
6d98843b31
[Responses API] Disable response store by default (#22137)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-08-03 04:04:21 -07:00
David Ben-David
aefeea0fde
[V1] [P/D] Refactor KV Connector Path (#21980)
Signed-off-by: David Ben-David <davidb@pliops.com>
Co-authored-by: David Ben-David <davidb@pliops.com>
2025-08-03 04:03:40 -07:00
H
24d1dffbeb
[executor] feat: add supports_pp attr to executors (#21786)
Signed-off-by: Haibin Lin <haibin.lin@bytedance.com>
2025-08-03 18:04:45 +08:00