Skip to content

Pull requests: google-deepmind/gemma

New pull request New
172 Open 339 Closed
172 Open 339 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Fix ChatSampler.conversation crash for non-Gemma4 tokenizers (breaks ToolSampler multi-turn)
#734 opened Jul 17, 2026 by sohumt123 Loading…
1
Fix infinite thinking loop, system prompt non-adherence, and multi-turn context loss for Gemma 4 (#727)
#732 opened Jul 16, 2026 by BhadaneAaditya Loading…
1
7
Cleanup protocols naming and convert Union types to Protocols.
#731 opened Jul 16, 2026 by copybara-service Bot Loading…
Reverses the order of operations in Embedder.encode_audio to match the upstream Gemax training configuration (Norm -> Projection, instead of Projection -> Norm).
#730 opened Jul 15, 2026 by copybara-service Bot Loading…
Internal
#729 opened Jul 15, 2026 by copybara-service Bot Loading…
Consolidate core API definitions into hd_api.py.
#728 opened Jul 15, 2026 by copybara-service Bot Loading…
Code update
#726 opened Jul 14, 2026 by copybara-service Bot Loading…
1
docs: add community health files and README updates
#724 opened Jul 9, 2026 by Mukller Loading…
1
Fix missing f-prefix in _normalize_token error message
#722 opened Jul 9, 2026 by HumphreySun98 Loading…
1
2
Use integer division for GQA reshape group size
#721 opened Jul 8, 2026 by HumphreySun98 Loading…
1
3
fixing text degeneration problem induced by positional gaps within kv cache for EB sampler.
#719 opened Jul 7, 2026 by copybara-service Bot Loading…
1
tests: relax RMSNorm tolerance to fix GPU precision failures
#718 opened Jul 5, 2026 by AbhishekGiri04 Loading…
1
fix: replace bare asserts with ValueError in _normalize_response (tool response parsing)
#716 opened Jul 5, 2026 by DhruvTilva Loading…
2
fix: Gemma4Sampler silently drops cache-full condition that Sampler always reported
#715 opened Jul 5, 2026 by DhruvTilva Loading…
fix(security): pin etils-actions/pypi-auto-publish to commit SHA in publish workflow
#710 opened Jun 28, 2026 by XananasX7 Loading…
1
Support non-tool use models with Sampler
#707 opened Jun 24, 2026 by PaulScemama Loading…
1
docs: fix broken relative links in hackable_diffusion_adapter AGENT.md
#706 opened Jun 23, 2026 by manumishra12 Loading…
1
chore: fix spelling typos in comments and docstrings
#705 opened Jun 23, 2026 by manumishra12 Loading…
Avoid JAX recompilation in Gemma4Sampler by padding audio statically.
#704 opened Jun 23, 2026 by copybara-service Bot Loading…
1
feat: add rolling cache turn pruning for ChatSampler (Issue #675)
#703 opened Jun 23, 2026 by Paramveersingh-S Loading…
1
Fix: Rolling KV cache and top-k logit trimming (fixes #675)
#698 opened Jun 14, 2026 by medmomoait Loading…
1
1
fix(t5gemma): add missing f-prefix in _normalize_token error message
#697 opened Jun 14, 2026 by Osamaali313 Loading…
2
Add sharding support to ChatSampler.
#696 opened Jun 12, 2026 by copybara-service Bot Loading…
Test
#693 opened Jun 11, 2026 by copybara-service Bot Loading…
Fix: Resolve KV Cache OOM & Logit Extraction Memory Spikes
#678 opened Jun 7, 2026 by prince-shakyaa Loading…
1
1
ProTip! Exclude everything labeled bug with -label:bug.