Commit Graph

2397 Commits

Author SHA1 Message Date
5fb68091db Merge remote-tracking branch 'origin/main' into one-pod-per-node-lb
# Conflicts:
#	.buildkite/test-pipeline.yaml
2025-07-23 15:52:27 +01:00
316b1bf706 [Tests] Add tests for headless internal DP LB (#21450)
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 07:49:25 -07:00
fb0cf7e212 rename test
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 14:57:34 +01:00
1c300fcf5a fix internal_dp_lb tests
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 14:55:02 +01:00
6328c808b8 CI tests for hybrid DPLB mode
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 12:12:42 +01:00
d95aedd533 [Tests] Add tests for headless internal DP LB
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 12:07:33 +01:00
2671334d45 [Model] add Hunyuan V1 Dense Model support. (#21368)
Signed-off-by: Asher Zhang <asherszhang@tencent.com>
2025-07-23 03:54:08 -07:00
1bd5f2f1ad Merge remote-tracking branch 'refs/remotes/origin/main' into one-pod-per-node-lb 2025-07-23 11:04:38 +01:00
6929f8b437 [Misc] fixed nvfp4_moe test failures due to invalid kwargs (#21246)
Signed-off-by: Yang Chen <yangche@fb.com>
2025-07-23 01:41:43 -07:00
32ec9e2f2a Mamba V2 Test not Asserting Failures. (#21379)
Signed-off-by: Yu Chin Fabian Lim <flim@sg.ibm.com>
2025-07-23 01:40:27 -07:00
accac82928 [Sampler] Introduce logprobs mode for logging (#21398)
Signed-off-by: Lu Fang <lufang@fb.com>
2025-07-23 01:39:25 -07:00
f63cc19210 fix handshake mock test
Signed-off-by: Nick Hill <nhill@redhat.com>
2025-07-23 08:08:40 +01:00
a1f3610fc6 [Core] Add basic unit test for maybe_evict_cached_block (#21400)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-07-23 00:02:02 -07:00
4ecedd1806 [Bugfix] Fix nightly transformers CI failure (#21427)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-07-23 00:01:01 -07:00
f154bb9ff0 Simplify weight loading in Transformers backend (#21382)
Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
2025-07-22 20:29:43 -07:00
c401c64b4c [CI/Build] Fix model executor tests (#21387)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-22 20:25:37 -07:00
4594fc3b28 [Model] Add Qwen3CoderToolParser (#21396)
Signed-off-by: simon-mo <xmo@berkeley.edu>
Co-authored-by: simon-mo <xmo@berkeley.edu>
2025-07-22 15:05:57 -07:00
35366ae57c [CI/Build] Fix test failure due to updated model repo (#21375)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-22 08:39:35 -07:00
2226d5bd85 [Bugfix] Decode Tokenized IDs to Strings for hf_processor in llm.chat() with model_impl=transformers (#21353)
Signed-off-by: ariG23498 <aritra.born2fly@gmail.com>
2025-07-22 08:27:28 -07:00
f38ee34a0a [feat] Enable mm caching for transformers backend (#21358)
Signed-off-by: raushan <raushan@huggingface.co>
2025-07-22 08:18:46 -07:00
774d0c014b [Perf] Cuda Kernel for Per Token Group Quant (#21083)
Signed-off-by: yewentao256 <zhyanwentao@126.com>
2025-07-22 07:27:15 -07:00
4fb56914c5 [perf] Add fused MLA QKV + strided layernorm (#21116)
Signed-off-by: Mickael Seznec <mickael@mistral.ai>
Co-authored-by: mgoin <mgoin64@gmail.com>
2025-07-22 07:07:44 -07:00
0df4d9b06b [Misc] unify variable for LLM instance v2 (#21356)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-07-22 06:32:36 -07:00
ed25054577 [Core] Introduce popleft_n and append_n in FreeKVCacheBlockQueue to further optimize block_pool (#21222)
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
2025-07-22 06:17:47 -07:00
bc8a8ce5ec [Misc] Remove deprecated args in v0.10 (#21349)
Signed-off-by: Kebe <mail@kebe7jun.com>
2025-07-22 05:26:39 -07:00
82b8027be6 Add arcee model (#21296)
Signed-off-by: alyosha-swamy <raghav@arcee.ai>
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
Co-authored-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-22 00:57:43 -07:00
488d8a986a [V1] [Hybrid] Add new test to verify that hybrid views into KVCacheTensor are compatible (#21300)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-07-21 23:31:18 -07:00
e7b2042681 Revert "[Performance] Performance improvements in non-blockwise fp8 CUTLASS MoE (#20762) (#21334)
Signed-off-by: Ming Yang <minos.future@gmail.com>
2025-07-21 21:49:01 -07:00
29d1ffc5b4 [DP] Fix Prometheus Logging (#21257)
Signed-off-by: Robert Shaw <robshaw@redhat.com>
Co-authored-by: Robert Shaw <robshaw@redhat.com>
2025-07-21 09:11:35 -07:00
6ece16c4fe [Misc] Add dummy maverick test (#21199)
Signed-off-by: Ming Yang <minos.future@gmail.com>
Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
2025-07-21 09:08:09 -07:00
a0e827e07c [BugFix] make utils.current_stream thread-safety (#21252) (#21253)
Signed-off-by: simpx <simpxx@gmail.com>
2025-07-21 09:07:36 -07:00
6dda13c86b [Misc] Add sliding window to flashinfer test (#21282)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-21 08:37:49 -07:00
6b46c4b653 Add Nvidia ModelOpt config adaptation (#19815)
Signed-off-by: Zhiyu Cheng <zhiyuc@nvidia.com>
2025-07-21 10:02:58 -04:00
d97841078b [Misc] unify variable for LLM instance (#20996)
Signed-off-by: Andy Xie <andy.xning@gmail.com>
2025-07-21 12:18:33 +01:00
042af0c8d3 [Model][1/N] Support multiple poolers at model level (#21227)
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
2025-07-21 02:22:21 -07:00
7ba34b1241 [bugfix] fix syntax warning caused by backslash (#21251) 2025-07-20 17:12:10 +00:00
9499e26e2a [Model] Support VLMs with transformers backend (#20543)
Signed-off-by: raushan <raushan@huggingface.co>
Signed-off-by: Isotr0py <2037008807@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Isotr0py <2037008807@qq.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Cyrus Leung <cyrus.tl.leung@gmail.com>
2025-07-20 13:25:50 +00:00
d1fb65bde3 Enable v1 metrics tests (#20953)
Signed-off-by: Seiji Eicher <seiji@anyscale.com>
2025-07-20 03:22:02 +00:00
3a1d8940ae [TPU] support fp8 kv cache quantization (#19292)
Signed-off-by: Chengji Yao <chengjiyao@google.com>
2025-07-20 03:01:00 +00:00
10eb24cc91 GLM-4 Update (#20736)
Signed-off-by: zRzRzRzRzRzRzR <2448370773@qq.com>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: Lu Fang <fanglu@fb.com>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Co-authored-by: Lu Fang <fanglu@fb.com>
2025-07-19 22:40:31 +00:00
752c6ade2e [V0 Deprecation] Deprecate BlockSparse Attention & Phi3-Small (#21217)
Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>
2025-07-19 13:53:17 -07:00
881e3cbe3b [V1] [Hybrid] Enable piecewise CUDA Graph for mamba layers (#21194)
Signed-off-by: Thomas Parnell <tpa@zurich.ibm.com>
2025-07-19 19:27:21 +00:00
9f414a12ad [BugFix] Make PD work with Ray (#21072)
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
2025-07-19 08:46:50 -07:00
c81259d33a Fix/remove some broken model executor tests (#21224)
Signed-off-by: Rabi Mishra <ramishra@redhat.com>
2025-07-19 12:15:07 +00:00
b3d82108e7 [Bugfix][Frontend] Fix openai CLI arg middleware (#21220)
Signed-off-by: 22quinn <33176974+22quinn@users.noreply.github.com>
2025-07-19 02:40:38 -07:00
7d94577138 Add torch golden impl for moe_align_block_size kernel test (#20653)
Signed-off-by: Shixian Cui <shixian@amazon.com>
Co-authored-by: Shixian Cui <shixian@amazon.com>
2025-07-19 02:32:36 -07:00
18e519ec86 [Bugfix] Fix ndarray video color from VideoAsset (#21064)
Signed-off-by: Isotr0py <2037008807@qq.com>
2025-07-19 02:17:16 -07:00
1eaff27815 [V0 deprecation] Remove long context LoRA (#21169)
Signed-off-by: Jee Jee Li <pandaleefree@gmail.com>
2025-07-19 02:15:41 -07:00
cf8cc32674 Fix a couple of Voxtral tests (#21218)
Signed-off-by: Huy Do <huydhn@gmail.com>
2025-07-19 09:13:41 +00:00
3e04107d97 [Model] EXAONE 4.0 model support (#21060)
Signed-off-by: Deepfocused <rlawhdrhs27@gmail.com>
Signed-off-by: woongsik <rlawhdrhs27@gmail.com>
2025-07-19 14:25:44 +08:00