 AlpinDale
|
acf2be3e44
chore: refactor llama3 rope
|
3 months ago |
 AlpinDale
|
9d9722b1c1
fix: metrics endpoint with RPC server (#747)
|
3 months ago |
|
AlpinDale
|
81c5f196eb
chore: various TPU fixes and optimizations (#746)
|
3 months ago |
|
AlpinDale
|
89a2c6dee1
chore: refactor `MultiModalConfig` initialization and profiling (#745)
|
3 months ago |
|
AlpinDale
|
1068597e8a
fix: minor bug fixes & clean-ups (#744)
|
3 months ago |
 Geun, Lim
|
08711d2ac9
feat: add Exaone model support (#743)
|
3 months ago |
|
AlpinDale
|
81c28d2a7f
fix: use nvml to get consistent device names (#739)
|
3 months ago |
|
AlpinDale
|
5559c5886f
fix: clear engine ref in RPC server (#738)
|
3 months ago |
|
AlpinDale
|
ef3a0f4cb1
fix: `custom_ar` check (#737)
|
3 months ago |
|
AlpinDale
|
ccbda97416
fix: types in AQLM and GGUF for dynamo support (#736)
|
3 months ago |
|
AlpinDale
|
9296d4b25d
feat: dynamo support for ScalarType (#733)
|
3 months ago |
|
AlpinDale
|
d9d85eeb6e
chore: register lora functions as torch ops (#732)
|
3 months ago |
|
AlpinDale
|
7a313483f1
chore: move update_flash_attn_metadata to attn backend (#731)
|
3 months ago |
|
AlpinDale
|
d34e083c48
feat: add experts_int8 support (#730)
|
3 months ago |
|
AlpinDale
|
b0f262eec1
feat: FP8 quantization support for AMD ROCm (#729)
|
3 months ago |
|
AlpinDale
|
c744443679
ci: bump to 0.6.1.post1 (#728)
|
3 months ago |
 miku448
|
9c0e7d95c8
fix: libcudart path for some versions of pytorch (#726)
|
3 months ago |
|
AlpinDale
|
4648f16c84
chore: fix return statement in Detokenizer class (#727)
|
3 months ago |
|
AlpinDale
|
a286adaeaa
feat: launch API server with uvloop (#725)
|
3 months ago |
|
AlpinDale
|
60b702a827
chore: register custom torch ops for flash-attn and flashinfer (#724)
|
3 months ago |
|
AlpinDale
|
8e0d376f1c
ci: bump aphrodite to 0.6.1 (#722)
|
3 months ago |
|
AlpinDale
|
12e40ae6fd
chore: update grafana template (#721)
|
3 months ago |
|
AlpinDale
|
61c7182491
feat: enable prompt logprobs in OpenAI API (#720)
|
3 months ago |
|
AlpinDale
|
28b6397188
chore: quant config for speculative draft models (#719)
|
3 months ago |
|
AlpinDale
|
8e22069c9e
fix: weight loading for scalars (#718)
|
3 months ago |
|
AlpinDale
|
d289c3855b
fix: install protobuf for cpu (#716)
|
3 months ago |
|
AlpinDale
|
008e646c7e
chore: add support for up to 2048 block size (#715)
|
3 months ago |
|
AlpinDale
|
1c519cc6ac
chore: set per-rank XLA cache for TPU (#714)
|
3 months ago |
|
AlpinDale
|
577586309d
chore: multi-step args and sequence modifications (#713)
|
3 months ago |
|
AlpinDale
|
0b8b407b6d
feat: support profiling with multiple multi-modal inputs per prompt (#712)
|
3 months ago |
