-
Notifications
You must be signed in to change notification settings - Fork 1.5k
Pull requests: Lightning-AI/litgpt
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Fix malformed <|im_start> token in Phi4Reasoning prompt style
#2267
opened Jun 16, 2026 by
JSap0914
Loading…
fix(finetune): all_reduce val loss across devices for initial and final validation
#2266
opened Jun 13, 2026 by
discobot
Loading…
fix: make convert_from_litgpt output loadable with AutoModel.from_pretrained
#2265
opened Jun 13, 2026 by
discobot
Loading…
fix(finetune): apply train.max_norm gradient clipping in finetune scripts
#2264
opened Jun 13, 2026 by
discobot
Loading…
ci: migrate PyPI release to trusted publishing (OIDC)
#2261
opened Jun 9, 2026 by
bhimrazy
Collaborator
Loading…
build(deps): bump the gha-updates group with 2 updates
CI / actions
Continuous integration
#2259
opened Jun 8, 2026 by
dependabot
Bot
Loading…
Omit ChatML system turn when there is no system message (Qwen3 emitted literal 'None')
#2258
opened Jun 5, 2026 by
lollinng
Loading…
Attempt to fix #2220: Enable Flash Attention in KV-cache path
#2248
opened May 9, 2026 by
woaiwang
Loading…
build(deps-dev): bump litdata from 0.2.59 to 0.2.61
dependencies
#2246
opened May 1, 2026 by
dependabot
Bot
Loading…
build(deps): update jsonargparse requirement from <=4.41,>=4.37 to >=4.37,<=4.48.0
dependencies
#2245
opened May 1, 2026 by
dependabot
Bot
Loading…
build(deps-dev): update transformers requirement from <4.57,>=4.51.3 to >=4.51.3,<5.8
dependencies
#2244
opened May 1, 2026 by
dependabot
Bot
Loading…
chore(model,prompts): add type annotations to module-level functions and __init__ methods
#2242
opened Apr 18, 2026 by
Koushik-Salammagari
Loading…
3 tasks done
chore(api): add type annotations to LLM class and module-level functions
#2241
opened Apr 18, 2026 by
Koushik-Salammagari
Loading…
3 tasks done
chore(data): add return type annotations to FLAN dataloader methods
#2240
opened Apr 18, 2026 by
Koushik-Salammagari
Loading…
3 tasks done
chore(utils): add type annotations to public functions in utils.py
#2237
opened Apr 14, 2026 by
nuthalapativarun
Loading…
docs(pretrain): add TinyStories pretraining section
#2236
opened Apr 14, 2026 by
nuthalapativarun
Loading…
fix(model): convert bool mask_cache to float additive mask for softcapping
#2235
opened Apr 14, 2026 by
nuthalapativarun
Loading…
Fix division by zero in LR scheduler when max_steps equals warmup_steps
#2212
opened Mar 9, 2026 by
Br1an67
Contributor
Loading…
Fix Mistral tokenizer missing spaces in decode_stream (Issue #1822)
#2211
opened Mar 5, 2026 by
mrshibly
Loading…
Fix IndexError in finetune scripts when last logit chunk becomes empty
#2141
opened Oct 4, 2025 by
Copilot
AI
Loading…
Previous Next
ProTip!
Updated in the last three days: updated:>2026-06-13.