pytorch torchchat issues

pytorch / torchchat

Run PyTorch LLMs locally on servers, desktop and mobile

BSD 3-Clause "New" or "Revised" License

3.4k stars 224 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

Torchchat on Android crashes on second prompt with Llama-3.2-3b-instruct

#1395 infil00p opened 2 hours ago
0
Typo fixes in native-execution.md

#1394 mikekgfb opened 1 day ago
1
Improvements for readability in ADVANCED-USERS.md

#1393 mikekgfb opened 1 day ago
1
Update quantization.md link to quantize.py

#1392 Jack-Khuu opened 3 days ago
1
Update multimodal.md to exercise server as part of test

#1391 mikekgfb opened 5 days ago
1
Changing the referenced AAR so that it uses the AAR from the docs

#1390 infil00p closed 2 days ago
3
Add missing include for compile on Ubuntu 24.04

#1389 infil00p closed 3 days ago
4
eval doc does not pass test

#1388 mikekgfb opened 6 days ago
1
Clarify messages in builder.py

#1387 mikekgfb closed 6 days ago
1
Fix English language usage in Runtime exception for builder.py

#1386 mikekgfb closed 5 days ago
2
Update dead link in https://github.com/pytorch/torchchat/blob/main/docs/quantization.md

#1385 yanbing-j opened 6 days ago
4
Update README.md to run and query server during test

#1384 mikekgfb opened 1 week ago
2
Update run-docs to enable `run-docs evaluation`

#1383 mikekgfb opened 1 week ago
1
Add multimodal to possible tests

#1382 mikekgfb closed 6 days ago
2
Integrate distributed inference with chat/server

#1381 mreso opened 1 week ago
1
What is the future plan of model expansion?

#1380 jenniew opened 1 week ago
3
Tokenizers cpp 1251

#1379 gabe-l-hart opened 1 week ago
1
Remove tokens per sec in aggregate_metrics when jit_compile

#1378 yanbing-j closed 6 days ago
7
Bug fix: Enable fast to override quantize json

#1377 Jack-Khuu closed 5 days ago
2
[RFC] Integration of Distributed Inference into TorchChat

#1376 mreso opened 1 week ago
4
fix: do not print perf stat when NaN

#1375 leseb closed 1 week ago
3
Bug Fix: Check for explicit cli device (fast)

#1374 Jack-Khuu closed 1 week ago
1
Torchchat generate cannot work with device=fast

#1373 jenniew closed 1 week ago
2
fix: mark model argument as mandatory

#1372 leseb closed 1 week ago
1
fix: remove dup dependency

#1371 leseb closed 1 week ago
1
fix: allow installing on python 3.12

#1370 leseb closed 1 week ago
2
Update Caching logic to only trigger on the first inference sample

#1369 Jack-Khuu closed 1 week ago
1
Minor typo + Update install_requirements.sh to support python 3.10 >=

#1368 Jack-Khuu closed 1 week ago
2
Bump PyTorch pin to 20241112

#1367 Jack-Khuu opened 1 week ago
14
Download fix

#1366 gabe-l-hart closed 6 days ago
1
AOTI filesize regression *.pt2 filesize is bigger than .*so

#1365 metascroy opened 2 weeks ago
2
bump pytorch nightly version

#1364 swolchok opened 2 weeks ago
4
Specifying dtype flag on export crashes AOTI export

#1363 metascroy closed 2 weeks ago
2
linear:int4 quantization regression testing

#1362 mikekgfb opened 2 weeks ago
4
Add Intel XPU device support to generate and serve

#1361 jenniew opened 2 weeks ago
9
AssertionError: Found multiple weight mapping files

#1360 DemonODG closed 6 days ago
7
Update cli.py to make --device/--dtype pre-empt quantize dict-specified values

#1359 mikekgfb closed 1 week ago
1
Create doc and tests for distributed inference

#1358 mikekgfb opened 2 weeks ago
1
Fails to export and run llama3.2-1b. RuntimeError: Failed to initialize zip archive: invalid header or archive is corrupted

#1357 siahuat0727 closed 3 days ago
4
`weights_only` default flip for `torch.load`

#1356 mikaylagawarecki opened 2 weeks ago
0
[WIP] Generate base class for better integration of distributed inference

#1355 mreso closed 1 week ago
7
Update contributor channel name

#1354 Gasoonjia closed 2 weeks ago
1
Remove last references to use_distributed argument

#1353 mreso closed 1 week ago
5
fix: add SIGINT handler

#1352 leseb closed 1 week ago
3
Periodic runs fail with workflow error: Invalid workflow file: .github/workflows/run-readme-periodic.yml#L50

#1351 mikekgfb opened 2 weeks ago
1
Create run-readme-pr-linuxaarch64

#1350 mikekgfb opened 2 weeks ago
3
Fast non-model CLI commands

#1349 gabe-l-hart closed 2 weeks ago
1
Minor code cleanups in generate.py and model.py

#1348 swolchok closed 2 weeks ago
1
Slow CLI --help (and other commands)

#1347 gabe-l-hart closed 2 weeks ago
0
fix: allow multiple weight mapping files for mistral

#1346 leseb closed 2 weeks ago
9