Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Upstream merge 25 02 17 #430

Merged
merged 112 commits into from
Feb 17, 2025
Merged

Upstream merge 25 02 17 #430

merged 112 commits into from
Feb 17, 2025

Conversation

gshtras
Copy link
Collaborator

@gshtras gshtras commented Feb 17, 2025

Including preliminary vllm-project#13348 merge to fix errors in the log upon loading local models

hmellor and others added 30 commits February 11, 2025 18:02
@hmellor
[Doc] Improve OpenVINO installation doc (vllm-project#13102)
deb6c1c 
Signed-off-by: Harry Mellor <[email protected]>
@terrytangyuan
[Bugfix] Guided decoding falls back to outlines when fails to import …
14ecab5 
…xgrammar (vllm-project#12976)

Signed-off-by: Yuan Tang <[email protected]>
@russellb
[Misc] Move pre-commit suggestion back to the end (vllm-project#13114)
72c2b68 
Signed-off-by: Russell Bryant <[email protected]>
@youngkent
[RFC][vllm-API] Support tokenizer registry for customized tokenizer i…
3ee696a 
…n vLLM (vllm-project#12518)

Signed-off-by: Keyun Tong <[email protected]>
@christian-pinto
[Model] IBM/NASA Prithvi Geospatial model (vllm-project#12830)
974dfd4
@khluu
[ci] Add more source file dependencies for some tests (vllm-project#1…
842b0fd 
…3123)

Signed-off-by: <>
Co-authored-by: EC2 Default User <[email protected]>
@lingfanyu
[Neuron][Kernel] Support Longer Sequences in NKI-based Flash PagedAtt…
e92694b 
…ention and Improve Efficiency (vllm-project#12921)

Signed-off-by: Lingfan Yu <[email protected]>
@dependabot
Bump helm/kind-action from 1.10.0 to 1.12.0 (vllm-project#11612)
a0597c6
@dependabot
Bump actions/stale from 9.0.0 to 9.1.0 (vllm-project#12462)
dd3b4a0
@dependabot
Bump helm/chart-testing-action from 2.6.1 to 2.7.0 (vllm-project#12463)
0c7d9ef
@dependabot
Bump actions/setup-python from 5.3.0 to 5.4.0 (vllm-project#12672)
d59def4
@maxdebayser
Further reduce the HTTP calls to huggingface.co (vllm-project#13107)
7c4033a
@842974287
[Misc] AMD Build Improvements (vllm-project#12923)
f1042e8
@bnellnm
[Bug] [V1] Try fetching stop_reason from EngineOutput before checking…
f4d97e4 
… the request (vllm-project#13108)
@DarkLight1337
[Bugfix] Fix num video tokens calculation for Qwen2-VL (vllm-project#…
985b4a2 
…13148)

Signed-off-by: DarkLight1337 <[email protected]>
@rafvasq
[Frontend] Generate valid tool call IDs when using `tokenizer-mode=mi…
314cfad 
…stral` (vllm-project#12332)
@jeejeelee
[Misc] Delete unused LoRA modules (vllm-project#13151)
82cabf5
@houseroad
Introduce VLLM_CUDART_SO_PATH to allow users specify the .so path (vl…
042c341 
…lm-project#12998)

Signed-off-by: Lu Fang <[email protected]>
@russellb
[CI/Build] Use mypy matcher for pre-commit CI job (vllm-project#13162)
2c2b560 
Signed-off-by: Russell Bryant <[email protected]>
@Qubitium
[CORE] [QUANT] Support for GPTQModel's dynamic quantization per mod…
36a0863 
…ule override/control (vllm-project#7086)
@mgoin
[Bugfix] Allow fallback to AWQ from AWQMarlin at per-layer granularity (
09972e7 
vllm-project#13119)
@mgoin
[CI] Fix failing FP8 cpu offload test (vllm-project#13170)
14b7899 
Signed-off-by: mgoin <[email protected]>
@andoorve
[V1][Bugfix] Copy encoder input ids to fix set iteration issue during…
4c0d93f 
… VLM abort (vllm-project#13173)

Signed-off-by: andoorve <[email protected]>
@russellb
[CI/Build] Ignore ruff warning up007 (vllm-project#13182)
8eafe5e 
Signed-off-by: Russell Bryant <[email protected]>
@khluu
[perf-benchmark] cleanup unused Docker images and volumes in H100 ben…
9f9704d 
…chmark instance (vllm-project#12706)
@kaixih
[NVIDIA] Support nvfp4 quantization (vllm-project#12784)
4fc5c23
@mgoin
[Bugfix][Example] Fix GCed profiling server for TPU (vllm-project#12792)
d88c866 
Signed-off-by: mgoin <[email protected]>
@Isotr0py
[VLM] Implement merged multimodal processor for Mllama (vllm-project#…
bc55d13 
…11427)
@houseroad
Simplify logic of locating CUDART so file path (vllm-project#13203)
009439c 
Signed-off-by: Lu Fang <[email protected]>
@comaniac
[Build] Automatically use the wheel of the base commit with Python-on…
60c68df 
…ly build (vllm-project#13178)
wchen61 and others added 21 commits February 16, 2025 08:59
@wchen61
[BugFix] Enhance test_pos_encoding to support execution on multi-devi…
dc0f7cc 
…ces (vllm-project#13187)

Signed-off-by: wchen61 <[email protected]>
@ywang96
[V1] Update doc and examples for H2O-VL (vllm-project#13349)
b7d3098 
Signed-off-by: Roger Wang <[email protected]>
@youkaichao
[ci] skip failed tests for flashinfer (vllm-project#13352)
124776e 
Signed-off-by: youkaichao <[email protected]>
@youkaichao
[platform] add base class for communicators (vllm-project#13208)
a0231b7 
Signed-off-by: youkaichao <[email protected]>
@DarkLight1337
[Bugfix] Fix 2 Node and Spec Decode tests (vllm-project#13341)
5d2965b 
Signed-off-by: DarkLight1337 <[email protected]>
@arkylin
[Docs] Change myenv to vllm. Update python_env_setup.inc.md (vllm-pro…
da833b0 
…ject#13325)
@WoosukKwon
[V1][BugFix] Add __init__.py to v1/spec_decode/ (vllm-project#13359)
7b89386 
Signed-off-by: Woosuk Kwon <[email protected]>
@WoosukKwon
[V1][PP] Cache Intermediate Tensors (vllm-project#13353)
e18227b 
Signed-off-by: Woosuk Kwon <[email protected]>
@Isotr0py
[Bugfix][Platform][CPU] Fix cuda platform detection on CPU backend ed…
d67cc21 
…ge case (vllm-project#13358)

Signed-off-by: Isotr0py <[email protected]>
@WoosukKwon
[V1][BugFix] Clean up rejection sampler & Fix warning msg (vllm-proje…
69e1d23 
…ct#13362)

Signed-off-by: Woosuk Kwon <[email protected]>
@jeejeelee
[V1][Misc] Avoid unnecessary log output (vllm-project#13289)
2010f04
@ShangmingCai
[Feature][Spec Decode] Simplify the use of Eagle Spec Decode (vllm-pr…
46cdd59 
…oject#12304)

Signed-off-by: Shangming Cai <[email protected]>
@yankooo
Fix spelling error in index.md (vllm-project#13369)
f857311
@huydhn
Run v1 benchmark and integrate with PyTorch OSS benchmark database (v…
4518683 
…llm-project#13068)

Signed-off-by: Huy Do <[email protected]>
@MengqingCao
[MISC] tiny fixes (vllm-project#13378)
238dfc8
@DarkLight1337
[VLM] Check required fields before initializing field config in `Dict…
7b623fc 
…EmbeddingItems` (vllm-project#13380)
@tlrmchlsmth @fabianlim
[Model] Support Mamba2 (Codestral Mamba) (vllm-project#9292)
1f69c4a 
Signed-off-by: Tyler Michael Smith <[email protected]>
Co-authored-by: Yu Chin Fabian Lim <[email protected]>
@yma11
[Bugfix] fix xpu communicator (vllm-project#13368)
30513d1 
Signed-off-by: yan ma <[email protected]>
@r4ntix
[Bugfix] Fix VLLM_USE_MODELSCOPE issue (vllm-project#13384)
ce77eb9
@gshtras
Merge remote-tracking branch 'upstream/main' into upstream_merge_25_0…
ce342c7 
…2_17
@gshtras
Merge remote-tracking branch 'Isotr0py/local-lookup' into upstream_me…
669fc3f 
…rge_25_02_17
@gshtras gshtras merged commit 365687d into main Feb 17, 2025
4 of 5 checks passed
@gshtras gshtras deleted the upstream_merge_25_02_17 branch February 20, 2025 19:10
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@shajrawi shajrawi shajrawi approved these changes

@Alexei-V-Ivanov-AMD Alexei-V-Ivanov-AMD Awaiting requested review from Alexei-V-Ivanov-AMD Alexei-V-Ivanov-AMD is a code owner

@maleksan85 maleksan85 Awaiting requested review from maleksan85 maleksan85 is a code owner

@divakar-amd divakar-amd Awaiting requested review from divakar-amd divakar-amd is a code owner

@charlifu charlifu Awaiting requested review from charlifu charlifu is a code owner

@mawong-amd mawong-amd Awaiting requested review from mawong-amd mawong-amd is a code owner

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.