Commits · 537c9755a736b4e206107a99e1c8961448a3d63b · norm / vllm · GitLab

"benchmark/matmul_fp8/README.md" did not exist on "4ca6c1311796a1342867ca43204cc2cfca376d6e"

26 Dec, 2023 1 commit
- [BUGFIX] Fix the path of test prompts (#2273) · 4aaafdd2
  Zhuohan Li authored Dec 27, 2023
  
  4aaafdd2
13 Dec, 2023 1 commit
- [BugFix] Fix input positions for long context with sliding window (#2088) · f1c85201
  Woosuk Kwon authored Dec 13, 2023
  
  f1c85201
20 Nov, 2023 1 commit
- Migrate linter from `pylint` to `ruff` (#1665) · 5ffc0d13
  Simon Mo authored Nov 20, 2023
  
  5ffc0d13
16 Oct, 2023 1 commit
- Implement prompt logprobs & Batched topk for computing logprobs (#1328) · 9d9072a0
  Zhuohan Li authored Oct 16, 2023
```
Co-authored-by: Yunmo Chen <16273544+wanmok@users.noreply.github.com>
```
  9d9072a0
02 Oct, 2023 1 commit
- TP/quantization/weight loading refactor part 1 - Simplify parallel linear logic (#1181) · ba0bfd40
  Zhuohan Li authored Oct 02, 2023
  
  ba0bfd40
06 Sep, 2023 1 commit
- Use queue for finished requests (#957) · c9927c1a
  Antoni Baum authored Sep 05, 2023
  
  c9927c1a
05 Sep, 2023 1 commit
- Align vLLM's beam search implementation with HF generate (#857) · 002800f0
  Zhuohan Li authored Sep 04, 2023
  
  002800f0
01 Sep, 2023 1 commit
- Add tests for models (#922) · 32b6816e
  Woosuk Kwon authored Sep 01, 2023
  
  32b6816e