-
Notifications
You must be signed in to change notification settings - Fork 288
Pull requests: InternLM/lmdeploy
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
feat: support llama2 and internlm2 on 910B (#1889)
#1972
opened Jul 9, 2024 by
lvhan028
Loading…
updated Jul 9, 2024
torch engine optimize prefill for long context
improvement
#1962
opened Jul 9, 2024 by
grimoire
Loading…
updated Jul 9, 2024
fix mixtral and mistral cache_position
Bug:P1
#1941
opened Jul 7, 2024 by
zhyncs
Loading…
updated Jul 9, 2024
support internlm-xcomposer2d5-7b
enhancement
New feature or request
#1932
opened Jul 5, 2024 by
irexyc
Loading…
updated Jul 9, 2024
4 of 5 tasks
refactor sampling layer setup
improvement
#1912
opened Jul 3, 2024 by
irexyc
Loading…
updated Jul 9, 2024
support min_p sampling & do_sample setting
#1966
opened Jul 9, 2024 by
irexyc
Loading…
updated Jul 9, 2024
Support glm 4v
enhancement
New feature or request
#1947
opened Jul 8, 2024 by
RunningLeon
Loading…
updated Jul 8, 2024
Support guided decoding for pytorch backend
enhancement
New feature or request
#1856
opened Jun 26, 2024 by
AllentDan
Loading…
updated Jul 8, 2024
Remove deprecated arguments from API and clarify model_name and chat_template_name
BC-breaking
improvement
WIP
#1931
opened Jul 5, 2024 by
lvhan028
Loading…
updated Jul 5, 2024
feat: decouple input_ids and output_ids
#1855
opened Jun 25, 2024 by
zhyncs
Loading…
updated Jul 4, 2024
Fix index error when profiling token generation with
-ct 1
Bug:P1
#1898
opened Jul 2, 2024 by
lvhan028
Loading…
updated Jul 2, 2024
Add Jetson platform support (by docker)
#1820
opened Jun 21, 2024 by
BestAnHongjun
Loading…
updated Jun 21, 2024
feat: skip invokeFlattenKV_v2_ when fp16 and bf16 with CacheType::kBlock
#1683
opened May 29, 2024 by
zhyncs
Loading…
updated Jun 5, 2024
Log stats
enhancement
New feature or request
#1423
opened Apr 11, 2024 by
AllentDan
Loading…
updated Jun 4, 2024
Check base64 image validation
Bug:P2
#1615
opened May 20, 2024 by
AllentDan
Loading…
updated May 22, 2024
[benchmark] optimize benchmark: counting tokenlizer tokens and error requests
#1607
opened May 17, 2024 by
NiuBlibing
Loading…
updated May 21, 2024
fix: update api_server_backend.py to adapt latest gradio
improvement
#1541
opened May 3, 2024 by
kv-chiu
Loading…
updated May 7, 2024
support AI4Chem/ChemLLM-7B-Chat-1_5-SFT
WIP
#1552
opened May 7, 2024 by
lvhan028
Loading…
updated May 7, 2024
Add docs of support new vl model
documentation
Improvements or additions to documentation
#1332
opened Mar 22, 2024 by
irexyc
Loading…
updated Apr 5, 2024
Compatible with Gradio 4.x
improvement
WIP
#1035
opened Jan 24, 2024 by
irexyc
Loading…
updated Apr 5, 2024
Previous Next
ProTip!
Type g p on any issue or pull request to go back to the pull request listing page.