Upstream merge 24 12 16#330
Merged
gshtras merged 102 commits intomain from upstream_merge_24_12_16Dec 16, 2024
+10,604-4,101
Commits
Commits on Dec 9, 2024
Commits on Dec 10, 2024
[Model] Add has_weight to RMSNorm and re-enable weights loading tracker for Mamba (vllm-project#10739)
authored- authored
- authored
- authored
- authored
- authored
[Bugfix] Fix xgrammar failing to read a vocab_size from LlavaConfig on PixtralHF. (vllm-project#11043)
authored- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Dec 11, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Dec 12, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Dec 13, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
[Core] support LoRA and prompt adapter in content-based hashing for Block Manager v2 prefix caching (vllm-project#8240)
authored[Bugfix] using len(tokenizer) instead of tokenizer.vocab_size in AllowedTokenIdsLogitsProcessor (vllm-project#11156)
authored- authored
- authored
- authored
[Distributed] Allow the placement group more time to wait for resources to be ready (vllm-project#11138)
authored
Commits on Dec 14, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
- authored
[Performance][Core] Optimize the performance of evictor v1 and v2 by applying a priority queue and lazy deletion (vllm-project#7209)
authored
Commits on Dec 15, 2024
- authored
- authored
- authored
- authored
- authored
- authored
- authored
Commits on Dec 16, 2024
- authored
- authored
- authored
- authored
- authored
- committed
- committed
- committed