issues
search
PygmalionAI
/
aphrodite-engine
PygmalionAI's large-scale inference engine
https://pygmalion.chat
GNU Affero General Public License v3.0
606
stars
78
forks
source link
issues
Recently updated
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
[Bug]: Flash attention cannot be used on v0.5.3
#468
Nero10578
opened
5 days ago
6
[Bug]: torch._dynamo.exc.BackendCompilerFailed with command-r-plus
#472
heungson
opened
1 day ago
0
[Bug]: Cannot load 70b exl2 5bpw model across 4 GPUs.
#471
Ph0rk0z
opened
3 days ago
7
[Bug]: GPUExecutor throwing 'TypeError: 'type' object is not subscriptable' on 0.5.3
#470
xyzkpsf
closed
2 days ago
2
[Installation]: Upload Aphrodite v0.5.2 On Pypi.org
#451
Abulhanan
closed
2 days ago
3
[Bug]: Converting gguf to state_dict
#411
heungson
opened
1 month ago
8
Fix recursion errors with large amounts of blocks
#459
thomas-xin
closed
5 days ago
3
Installation fails on NAVI gpu
#345
Naomiusearch
closed
5 days ago
2
Fix quants installation on ROCM
#469
Naomiusearch
closed
5 days ago
1
[Usage]: What to set to get acceptable performance on Pascal GPUs? (Non-P100)
#452
Nero10578
closed
5 days ago
2
[Installation]: Installing from source does not work. undefined symbol: _ZN3c104cuda14ExchangeDeviceEa
#453
Nero10578
closed
5 days ago
8
feat: add batch tokenization endpoint along with option for no token ids
#450
ahme-dev
closed
5 days ago
0
[WIP] feat: Mamba support
#419
AlpinDale
closed
5 days ago
1
[Feature]: actual working health endpoint
#390
mrseeker
closed
5 days ago
2
[Feature]: Add support for DBRX model
#385
BlairSadewitz
closed
5 days ago
2
[Feature]: Add support for Qwen2MoE
#387
StableFluffy
closed
5 days ago
1
[Bug]: Unable to use OpenAI API with an auth key via a web browser due to OPTIONS preflight request returning 401.
#434
LostRuins
closed
5 days ago
1
[Bug]:
#435
someoneexistsontheinternet
opened
3 weeks ago
1
[Bug]: PermissionError: [Errno 13] Permission denied: '/app/aphrodite-engine/.triton'
#458
theobjectivedad
closed
6 days ago
3
[v0.5.3] Release Candidate
#388
AlpinDale
closed
6 days ago
1
[Bug]: Does --trust-remote-code work?
#357
BlairSadewitz
closed
6 days ago
1
Dockerfile: permission update, configurable build jobs, torch 2.3.0
#465
theobjectivedad
closed
6 days ago
5
Fix Navi support
#466
Naomiusearch
closed
6 days ago
1
Initial fetch for `config.json` ignores `--revision`?
#318
josephrocca
opened
2 months ago
13
[WIP] feat: T5 support
#255
AlpinDale
opened
3 months ago
1
Bump `torch` to 2.3.0
#467
AlpinDale
closed
1 week ago
0
feat: SmoothQuant support
#251
AlpinDale
closed
1 week ago
0
[WIP] feat: Intel GPU support via SYCL
#194
AlpinDale
closed
1 week ago
0
feat: ARM CPU support
#182
AlpinDale
closed
1 week ago
1
Refactor: Quantization
#454
AlpinDale
closed
1 week ago
1
[Usage]: Lora Adapter Parameter while inferencing
#464
alokgupta1996
closed
1 week ago
1
[Bug]: LoRA fails to load
#461
kubernetes-bad
closed
1 week ago
1
[Feature]: Exllamav2 Q4 cache
#463
Anthonyg5005
opened
1 week ago
2
fix: lora errors
#462
AlpinDale
closed
1 week ago
0
Fix minor bugs in outlines and lmfe.
#449
sgsdxzy
closed
1 week ago
1
[Bug]: LoRA broken when TP>1
#460
kubernetes-bad
opened
1 week ago
0
Fixed REVISION variable not being passed on.
#456
houmie
closed
1 week ago
0
Fix to https://github.com/PygmalionAI/aphrodite-engine/issues/318
#455
houmie
closed
1 week ago
3
[sparsetral and Qwen2idae]: support for mixtral of lora
#330
sorasoras
opened
2 months ago
27
[Feature]: Is there a reason CUDA 6.1 is the minimum? Would CUDA 6.0 on the P100 not work?
#413
Nero10578
opened
1 month ago
5
Proof of Concept: Recovering the missing KV block space
#262
50h100a
closed
3 months ago
1
Mirostat v2 Fix
#73
50h100a
closed
6 months ago
2
fix logit bias logitproc
#278
50h100a
closed
2 months ago
1
Mirostat v2 Rewrite
#334
50h100a
closed
1 month ago
3
Greatly improve KV cache size in low-memory environments
#335
50h100a
closed
2 months ago
1
[Installation]: ValueError: 17 is not a valid GGMLQuantizationType
#448
Abulhanan
closed
2 weeks ago
21
[Performance]: Memory Usage Fix for gguf.
#447
Abulhanan
closed
2 weeks ago
3
[Bug]: gguf loading failed. config.json?
#417
juud79
opened
1 month ago
4
chore: clean up the quants
#440
AlpinDale
closed
2 weeks ago
0
fix: restore backwards compatibility with sm_60 (P100 and GP100)
#444
AlpinDale
closed
2 weeks ago
1
Next