ywang96
Follow
Pinned Loading
708 contributions in the last year
Less
No contributions.
Low contributions.
Medium-low contributions.
Medium-high contributions.
High contributions.
More
Activity overview
Loading
Contribution activity
March 2025
Created 1 commit in 1 repository
Created a pull request in vllm-project/vllm that received 7 comments
[Misc][V1] Avoid using envs.VLLM_USE_V1 in mm processing
The main difference between V0 and V1 multimodal input processing is that in V1 we need mm_hashes for downstream tasks (prefix caching, feature cac…
+38
−8
lines changed
•
7
comments
Reviewed 13 pull requests in 1 repository
vllm-project/vllm
13 pull requests
-
[Doc] Fix a typo
This contribution was made on Mar 7
-
[BUGFIX] Skip tokenization support for throughput benchmark
This contribution was made on Mar 5
-
[Bugfix][V1] Fix allowed_token_ids for v1 Sampler
This contribution was made on Mar 5
-
[V1] V1 Enablement Oracle
This contribution was made on Mar 5
-
[Misc][V1] Avoid using
envs.VLLM_USE_V1in mm processingThis contribution was made on Mar 5 -
[Model] New model support for Phi-4-multimodal-instruct
This contribution was made on Mar 4
-
[V1][Bugfix] Do not reset prefix caching metrics
This contribution was made on Mar 4
-
[V1][Molmo] Fix get_multimodal_embeddings() in molmo.py
This contribution was made on Mar 4
-
[sleep mode] error out with expandable_segments
This contribution was made on Mar 4
-
[Model] Extend Ultravox to accept audio longer than 30s
This contribution was made on Mar 4
-
[Misc] typo find in deepseek_v2
This contribution was made on Mar 3
-
[Doc] V1 user guide
This contribution was made on Mar 2
-
[Misc] Accurately capture the time of loading weights
This contribution was made on Mar 1
Created an issue in vllm-project/vllm that received 1 comment
[Usage]: Clean up Engine Args & Documentation
Your current environment Currently vLLM has a lot of engine arguments listed here https://docs.vllm.ai/en/latest/serving/engine_args.html. Over tim…
•
1
comment