Skip to content

Pull requests: nod-ai/shark-ai

New pull request New
104 Open 1,162 Closed
104 Open 1,162 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

Bump IREE requirement pins to 3.5.0rc20250523
#1510 opened May 23, 2025 by shark-pr-automator bot Loading…
Handle more datatypes gracefully in the dump_gguf tool
#1508 opened May 22, 2025 by KyleHerndon Loading…
More Deepseek Perplexity Tests
#1507 opened May 22, 2025 by Alex-Vasile • Draft
1 task
[sharktank] Fix module patching and safetensors comparison tool
#1506 opened May 22, 2025 by sogartar Loading…
[sharktank] Add Deepseek sharding changes
#1499 opened May 21, 2025 by archana-ramalingam Loading…
10
Fix multi hypothesis streaming
#1496 opened May 21, 2025 by zphoenixrises • Draft
Fix how fp8 attention quantizers are used
#1494 opened May 21, 2025 by KyleHerndon Loading…
2
[sharktank] Add mixture of experts(moe) support for Llama 4 model
#1491 opened May 21, 2025 by vivekkhandelwal1 Loading…
30
[sharktank] Add missing argument device affinity for tensor-parallel Resnet block test
#1490 opened May 21, 2025 by sogartar • Draft
Create CODEOWNERS
#1478 opened May 20, 2025 by Groverkss Loading…
Integrate MLIR kernel for KV cache gather
#1468 opened May 16, 2025 by rsuderman • Draft
[Shortfin][LLM] Add initial support for disaggregated invocations
#1463 opened May 16, 2025 by vinayakdsci • Draft
Testing for parity between cli and server
#1459 opened May 16, 2025 by zphoenixrises • Draft
Fuse transposition into first indexing for kv cache read
#1456 opened May 16, 2025 by rsuderman Loading…
Fastapi separate process
#1448 opened May 15, 2025 by zphoenixrises • Draft
1
Create Program for each logical device
#1440 opened May 14, 2025 by dezhiAmd • Draft
1
Changes workers flag to shortfin_workers
#1431 opened May 12, 2025 by IanNod Loading…
4
rework threading for stuff
#1429 opened May 12, 2025 by rsuderman • Draft
Separate prefill and decode fiber pools
#1417 opened May 9, 2025 by IanNod Loading…
Move awaits out of loop
#1416 opened May 8, 2025 by zphoenixrises Loading…
[WIP] Enable execution on multiple HIP streams on one physical device
#1412 opened May 8, 2025 by vinayakdsci • Draft
Use multiple logical devices to handle ClientGenerateBatchProcess
#1403 opened May 7, 2025 by dezhiAmd • Draft
1
Add multiprocess support
#1394 opened May 6, 2025 by daveliddell Loading…
[shortfin][LLM] Support multiple HIP streams
#1391 opened May 5, 2025 by vinayakdsci Loading…
9
Update llama_serving.md doc to reflect the latest changes
#1386 opened May 5, 2025 by pravg-amd Loading…
2
ProTip! Filter pull requests by the default branch with base:main.