| .. |
|
custom_kernels
|
Add RoCm support (#1243)
|
2023-11-27 14:08:12 +01:00 |
|
exllama_kernels
|
GPTQ support on ROCm (#1489)
|
2024-01-26 16:27:44 +01:00 |
|
exllamav2_kernels
|
GPTQ support on ROCm (#1489)
|
2024-01-26 16:27:44 +01:00 |
|
tests
|
Fixing non divisible embeddings. (#1476)
|
2024-01-24 13:08:41 +01:00 |
|
text_generation_server
|
GPTQ support on ROCm (#1489)
|
2024-01-26 16:27:44 +01:00 |
|
.gitignore
|
Support eetq weight only quantization (#1068)
|
2023-09-27 11:42:57 +02:00 |
|
Makefile
|
feat: bump lock and requirement files
|
2024-01-26 11:23:49 -05:00 |
|
Makefile-awq
|
Add AWQ quantization inference support (#1019) (#1054)
|
2023-09-25 15:31:27 +02:00 |
|
Makefile-eetq
|
Support eetq weight only quantization (#1068)
|
2023-09-27 11:42:57 +02:00 |
|
Makefile-flash-att
|
Add RoCm support (#1243)
|
2023-11-27 14:08:12 +01:00 |
|
Makefile-flash-att-v2
|
`make install-flash-attn-v2-cuda` should work like `make install-flash-attn-v2` used to work. (#1294)
|
2023-11-28 16:28:40 +01:00 |
|
Makefile-vllm
|
Speculative (#1308)
|
2023-12-11 12:46:30 +01:00 |
|
README.md
|
feat(router): refactor API and add openAPI schemas (#53)
|
2023-02-03 12:43:37 +01:00 |
|
poetry.lock
|
feat: bump lock and requirement files
|
2024-01-26 11:23:49 -05:00 |
|
pyproject.toml
|
feat: adds phi model (#1442)
|
2024-01-25 15:37:53 +01:00 |
|
requirements_common.txt
|
fix: ensure latest requirements exported
|
2024-01-26 11:26:34 -05:00 |
|
requirements_cuda.txt
|
fix: ensure latest requirements exported
|
2024-01-26 11:26:34 -05:00 |
|
requirements_rocm.txt
|
fix: ensure latest requirements exported
|
2024-01-26 11:26:34 -05:00 |
fc86dba781