issues
search
neuralmagic
/
deepsparse
Sparsity-aware deep learning inference runtime for CPUs
https://neuralmagic.com/deepsparse/
Other
2.94k
stars
169
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
log warning for batch_size 1
#1503
horheynm
opened
6 months ago
7
Add LLMPerf example for DeepSparse LLM Server
#1502
mgoin
closed
6 months ago
0
Unsupported ONNX type 10 for FP16
#1501
farizalmustaqim
closed
3 months ago
5
Add CLIP model to enable test_clip.py
#1500
mgoin
opened
6 months ago
1
Replace Fastchat Chat Templates with HF `apply_chat_template`
#1499
mgoin
closed
6 months ago
0
Bump gradio from 3.19.1 to 4.11.0 in /examples/benchmark-ui
#1498
dependabot[bot]
closed
6 months ago
1
Let OpenAI ChatCompletionRequest accept List[Dict] messages
#1497
mgoin
closed
6 months ago
0
Correct token usage reporting for OpenAI server
#1496
mgoin
closed
6 months ago
1
[Fix][Text Generation] Fixing failing OPT tests
#1495
dbogunowicz
closed
6 months ago
0
[Text Generation] Enable continuous batching when internal kv_cache is enabled
#1493
dsikka
closed
6 months ago
0
darft
#1492
horheynm
closed
7 months ago
0
Draft asyncio test
#1491
horheynm
closed
7 months ago
0
lint on readme
#1490
horheynm
closed
7 months ago
1
Read me lint
#1489
horheynm
closed
7 months ago
0
Readme lint
#1488
horheynm
closed
7 months ago
0
Add Text Gen Alias
#1487
dsikka
closed
7 months ago
3
[OpenAI][Server] Enable OpenAI text generation streaming
#1486
dsikka
closed
7 months ago
0
[Cherry-pick] Hotfix 1.6.1 for license changes
#1485
dhuangnm
closed
7 months ago
0
[Pipeline Refactor][Text Generation] Updating Pipeline Execution and Enable Streaming
#1484
dsikka
closed
7 months ago
1
[Text Generation][V2] NonKVCachePipeline
#1483
dbogunowicz
closed
6 months ago
0
Update router
#1482
dsikka
closed
7 months ago
0
[Pipeline Refactor] Update markdowns for QA
#1481
dsikka
closed
7 months ago
0
[Pipeline Refactor][Server] Enable from files for v2
#1480
dsikka
closed
7 months ago
0
V2/george scratch
#1479
horheynm
closed
7 months ago
0
[V2 Pipeline] SImple Asyncio pipeline test
#1478
horheynm
opened
7 months ago
0
[Pipeline Refactor][server][OpenAI] Enable OpenAI to use new text gen pipeline
#1477
dsikka
closed
7 months ago
0
[Text Generation][Pipeline Refactor] Causal Mask Check
#1476
dsikka
closed
7 months ago
0
[Text Generation][Pipeline Refactor] Add in prompt condition
#1475
dsikka
closed
7 months ago
0
[Text Generation][Pipeline Refactor] Add input tokens to output for perplexity
#1474
dsikka
closed
7 months ago
0
[Text Generation][Pipeline Refactor] Add kv_cache session full check
#1473
dsikka
closed
7 months ago
0
V2 Timer Manager
#1472
horheynm
closed
6 months ago
1
[V2 Pipeline] Middleware manager
#1471
horheynm
closed
6 months ago
1
[Pipeline Refactor] Fix circular import caused by `chat.py`
#1470
dsikka
closed
7 months ago
0
[V2 Pipeline] Fine-grained timer from inference state
#1469
horheynm
closed
6 months ago
1
[Pipeline Refactor][Text Generation] Add `parse_inputs` operator to TextGeneration
#1468
dsikka
closed
7 months ago
0
[PIpeline Refactor] Fix eval_downstream import
#1467
dsikka
closed
7 months ago
0
[Pipeline Refactor] Add in top level aliases
#1466
dsikka
closed
7 months ago
0
[Pipeline Refactor][server] Update deepsparse server to work with the new pipeline
#1465
dsikka
closed
7 months ago
0
Update config
#1464
dsikka
closed
7 months ago
0
dummy injection
#1463
horheynm
closed
7 months ago
0
[Benchmarking] Update `data_creation` to work with prompt alias in `text_generation`
#1462
dsikka
closed
7 months ago
0
Update YOLOv8 annotate.py
#1461
mgoin
closed
7 months ago
0
[Pipeline Refactor] Migration
#1460
dsikka
closed
7 months ago
0
more fixes
#1459
dsikka
closed
7 months ago
0
rebase fixes
#1458
dsikka
closed
7 months ago
0
[Pipeline Refactor] Add `Pipeline.create` method to initialize pipelines
#1457
dsikka
closed
7 months ago
0
bump up version to 1.7.0
#1456
dhuangnm
closed
7 months ago
0
[Fix] Adapt to the newest SparseZoo interface (and get GHA green again)
#1455
dbogunowicz
closed
7 months ago
0
[V2 Pipeline] Middleware Timer
#1454
horheynm
closed
7 months ago
0
[Pipeline Refactor] Fix Operator scheduling to fix issue with slow execution
#1453
dsikka
closed
7 months ago
0
Previous
Next