-
Notifications
You must be signed in to change notification settings - Fork 183
Pull requests: vllm-project/llm-compressor
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Autowrapper] Fix local names, increase reproducability
ready
When a PR is ready for review
#1672
opened Jul 22, 2025 by
kylesayrs
Loading…
[KV Cache] support kv cache int8 per channel quantization
ready
When a PR is ready for review
#1663
opened Jul 19, 2025 by
Eviannn
Loading…
Remove tracing blame when encountering runtime errors
#1655
opened Jul 17, 2025 by
kylesayrs
Loading…
[Examples] Remote
trust_remote_code
from people's speech dataset
#1654
opened Jul 17, 2025 by
kylesayrs
Loading…
Minor speedup for
infer_quantization_format
when save_compressed=False
#1636
opened Jul 10, 2025 by
kylesayrs
Loading…
add DeepseekV3 AWQ mapping
ready
When a PR is ready for review
#1619
opened Jul 3, 2025 by
cjackal
Loading…
Use torch.compile to speed up GPTQ algo
ready
When a PR is ready for review
#1561
opened Jun 17, 2025 by
aladerran
Loading…
AWQ minor performance improvements to smoothing
ready
When a PR is ready for review
#1557
opened Jun 16, 2025 by
brian-dellabetta
Loading…
Change deprecated name to When a PR is ready for review
has_offloaded_params
ready
#1556
opened Jun 16, 2025 by
kylesayrs
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2025-07-21.