-
Notifications
You must be signed in to change notification settings - Fork 737
Pull requests: InternLM/lmdeploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Fix] Include input_embeddings in prefix-cache identity
#4935
opened Sep 4, 2026 by
zjn20030811
Loading…
[Fix] Isolate Mooncake KV-store keys by cache identity
#4932
opened Sep 3, 2026 by
wildoranges
Loading…
6 tasks done
fix: initialize MLA KV-B after online FP8 quantization
Bug:P0
#4925
opened Sep 1, 2026 by
CUHKSZzxy
Collaborator
Loading…
Fix TurboMind vision workspace overflows
Bug:P0
#4924
opened Sep 1, 2026 by
irexyc
Collaborator
Loading…
feat: resolve oci:// model paths via llmman serve
#4922
opened Aug 30, 2026 by
ericcurtin
Loading…
3 of 6 tasks
Refactor PyTorch scheduler ownership and API boundaries
improvement
#4921
opened Aug 30, 2026 by
grimoire
Collaborator
Loading…
fix(disagg): make zmq_disconnect synchronous so p2p_drop_connect actually closes the sockets
#4916
opened Aug 28, 2026 by
Anai-Guo
Contributor
Loading…
feat: add symmetric-memory LM-head all-gather
improvement
#4915
opened Aug 28, 2026 by
qescccczmr
Collaborator
Loading…
3 tasks done
Fix AWQ checkpoint loading for Qwen3.5 fused GDN QKV projection
#4911
opened Aug 27, 2026 by
adityaanikam
Loading…
feat(gpt-oss): combine xgrammar structural_tag grammar with Harmony parser
improvement
#4907
opened Aug 27, 2026 by
windreamer
Collaborator
Loading…
feat: add XTuner TileLang sparse MLA backend
improvement
#4904
opened Aug 26, 2026 by
CUHKSZzxy
Collaborator
Loading…
feat(pytorch): add piecewise CUDA graph prefill
improvement
#4895
opened Aug 23, 2026 by
grimoire
Collaborator
Loading…
refactor(pytorch): replace backend operator builders with typed build specs
improvement
#4890
opened Aug 21, 2026 by
grimoire
Collaborator
Loading…
feat(metrics): expose prefix-cache eviction count as a Prometheus counter
#4888
opened Aug 20, 2026 by
SuperMarioYL
Contributor
Loading…
improve(autotest): replace APIClient with OpenAI SDK and strict param checks
#4887
opened Aug 20, 2026 by
littlegy
Contributor
Loading…
[ci] refactor(autotest): consolidate layout-based pytest cases
#4881
opened Aug 18, 2026 by
zhulinJulia24
Collaborator
Loading…
[Feature] Chunk-boundary states for gated-delta prefix caching
#4859
opened Aug 14, 2026 by
Tsundoku958
Contributor
Loading…
feat: support Intern-S2-Preview TS encoder
#4810
opened Jul 31, 2026 by
CUHKSZzxy
Collaborator
Loading…
refactor: stream tool parameters incrementally
improvement
#4802
opened Jul 29, 2026 by
lvhan028
Collaborator
Loading…
Previous Next
ProTip!
Filter pull requests by the default branch with base:main.