huggingface / text-generation-inference
File Age & Freshness

File age measurements show the distribution of file ages (days since the first commit) and the file freshness (days since the latest commit).

Summary
File Change History Overall
File Age Distribution Overall
Days since first update
  • There are 409 files with 98,155 lines of code in files.
    • 171 files that are 366+ days old (46,032 lines of code)
    • 99 files that are 181-365 days old (15,511 lines of code)
    • 113 files that are 91-180 days old (28,099 lines of code)
    • 22 files that are 31-90 days old (7,216 lines of code)
    • 4 files that are 1-30 days old (1,297 lines of code)
46% | 15% | 28% | 7% | 1%
Legend:
366+
181-365
91-180
31-90
1-30

explore: grouped by folders | grouped by age
File Freshness Distribution Overall
Days since last update
  • There are 409 files with 98,155 lines of code in files.
    • 56 files have been last changed 366+ days ago (5,384 lines of code)
    • 115 files have been last changed 181-365 days ago (23,399 lines of code)
    • 111 files have been last changed 91-180 days ago (20,981 lines of code)
    • 78 files have been last changed 31-90 days ago (26,249 lines of code)
    • 49 files have been last changed 1-30 days ago (22,142 lines of code)
5% | 23% | 21% | 26% | 22%
Legend:
366+
181-365
91-180
31-90
1-30

explore: grouped by folders | grouped by freshness
File Change History per File Extension
py, json, rs, md, yaml, cuh, toml, txt, nix, cu, sh, gitignore, cpp, h, hpp, cmake, js, ini, proto, mdx, dockerignore, html
File Age Distribution per Extension
Days since first update
366+
181-365
91-180
31-90
1-30
py44% | 9% | 35% | 9% | 1%
rs47% | 43% | 9% | 0% | 0%
cuh100% | 0% | 0% | 0% | 0%
cu99% | <1% | 0% | 0% | 0%
proto100% | 0% | 0% | 0% | 0%
cpp84% | 15% | 0% | 0% | 0%
toml47% | 33% | 19% | 0% | 0%
js50% | 50% | 0% | 0% | 0%
h100% | 0% | 0% | 0% | 0%
nix0% | 100% | 0% | 0% | 0%
hpp0% | 100% | 0% | 0% | 0%
cmake0% | 100% | 0% | 0% | 0%
File Freshness Distribution per Extension
Days since last update
366+
181-365
91-180
31-90
1-30
cuh100% | 0% | 0% | 0% | 0%
cu99% | <1% | 0% | 0% | 0%
py<1% | 26% | 21% | 24% | 27%
cpp84% | 0% | 15% | 0% | 0%
rs1% | 19% | 25% | 43% | 10%
proto44% | 55% | 0% | 0% | 0%
h100% | 0% | 0% | 0% | 0%
hpp0% | 52% | 47% | 0% | 0%
js0% | 100% | 0% | 0% | 0%
nix0% | 13% | 22% | 63% | 0%
toml0% | 11% | 51% | 23% | 13%
cmake0% | 9% | 90% | 0% | 0%
File Change History per Logical Decomposition
primary
primary (file age distribution)
Days since first update
366+
181-365
91-180
31-90
1-30
server77% | 13% | 7% | 1% | 0%
router78% | 12% | 9% | 0% | 0%
launcher99% | <1% | 0% | 0% | 0%
benchmark100% | 0% | 0% | 0% | 0%
clients100% | 0% | 0% | 0% | 0%
proto100% | 0% | 0% | 0% | 0%
ROOT49% | 50% | 0% | 0% | 0%
load_tests20% | 79% | 0% | 0% | 0%
backends0% | 18% | 61% | 17% | 3%
nix0% | 100% | 0% | 0% | 0%
primary (file freshness distribution)
Days since last update
366+
181-365
91-180
31-90
1-30
server10% | 40% | 24% | 24% | 0%
proto44% | 55% | 0% | 0% | 0%
benchmark15% | 84% | 0% | 0% | 0%
clients6% | 7% | 83% | 2% | 0%
launcher<1% | <1% | 1% | 0% | 96%
router<1% | 3% | 13% | 82% | 0%
backends0% | 6% | 19% | 22% | 51%
load_tests0% | 100% | 0% | 0% | 0%
nix0% | 20% | 33% | 45% | 0%
ROOT0% | 0% | 37% | 50% | 12%
Oldest Files (Top 50)
File# lines# unitscreatedlast modified# changes
(days)
# contributorsfirst
contributor
latest
contributor
server.rs
in router/src
2105 1 2022-10-11 2025-05-06 137 25 olivier@huggingface.co 15324346+regisss@users.nore...
validation.rs
in router/src
1186 9 2022-10-11 2025-05-01 78 9 olivier@huggingface.co david.richard.holtz@gmail.com
proto
208 - 2022-10-11 2024-06-04 33 5 olivier@huggingface.co olivier@huggingface.co
Cargo.toml
in router
73 - 2022-10-11 2025-02-18 52 9 olivier@huggingface.co 36760800+alvarobartt@users....
102 - 2022-10-14 2025-05-21 114 10 olivier@huggingface.co me@danieldk.eu
lib.rs
in router/src
1176 17 2022-10-17 2025-05-01 103 16 olivier@huggingface.co david.richard.holtz@gmail.com
main.rs
in launcher/src
1815 35 2022-10-18 2025-06-12 137 21 olivier@huggingface.co yuan.wu@intel.com
Cargo.toml
in root
49 - 2022-10-18 2025-06-19 67 10 olivier@huggingface.co david@huggingface.co
Cargo.toml
in launcher
25 - 2022-10-18 2025-03-04 30 7 olivier@huggingface.co hugo.larcher@huggingface.co
5 - 2022-10-18 2025-03-24 14 5 olivier@huggingface.co patry.nicolas@protonmail.com
__init__.py
in server/text_generation_server/models
1742 2 2023-03-07 2025-05-06 108 17 olivier@huggingface.co mohit21sharma.ms@gmail.com
seq2seq_lm.py
in server/text_generation_server/models
751 10 2023-03-07 2024-10-16 42 9 olivier@huggingface.co olivier@huggingface.co
causal_lm.py
in server/text_generation_server/models
713 10 2023-03-07 2024-12-03 49 10 olivier@huggingface.co me@danieldk.eu
client.py
in clients/python/text_generation
538 8 2023-03-07 2025-02-19 20 8 olivier@huggingface.co patry.nicolas@protonmail.com
tokens.py
in server/text_generation_server/utils
530 23 2023-03-07 2024-07-26 24 5 olivier@huggingface.co david.richard.holtz@gmail.com
cli.py
in server/text_generation_server
301 3 2023-03-07 2025-01-20 41 10 olivier@huggingface.co patry.nicolas@protonmail.com
server.py
in server/text_generation_server
270 5 2023-03-07 2025-05-06 42 7 olivier@huggingface.co mohit21sharma.ms@gmail.com
types.py
in clients/python/text_generation
263 13 2023-03-07 2025-03-05 25 9 olivier@huggingface.co patry.nicolas@protonmail.com
hub.py
in server/text_generation_server/utils
174 9 2023-03-07 2024-09-24 14 3 olivier@huggingface.co patry.nicolas@protonmail.com
model.py
in server/text_generation_server/models
146 7 2023-03-07 2025-03-18 29 7 olivier@huggingface.co mohit21sharma.ms@gmail.com
galactica.py
in server/text_generation_server/models
104 3 2023-03-07 2024-07-26 33 7 olivier@huggingface.co david.richard.holtz@gmail.com
types.py
in server/text_generation_server/models
89 10 2023-03-07 2024-10-16 11 4 olivier@huggingface.co olivier@huggingface.co
convert.py
in server/text_generation_server/utils
82 3 2023-03-07 2024-04-05 10 3 olivier@huggingface.co patry.nicolas@protonmail.com
dist.py
in server/text_generation_server/utils
80 8 2023-03-07 2025-04-15 10 4 olivier@huggingface.co yi.a.wang@intel.com
watermark.py
in server/text_generation_server/utils
70 6 2023-03-07 2023-08-16 5 2 olivier@huggingface.co patry.nicolas@protonmail.com
errors.py
in clients/python/text_generation
61 12 2023-03-07 2023-03-07 1 1 olivier@huggingface.co olivier@huggingface.co
inference_api.py
in clients/python/text_generation
55 4 2023-03-07 2024-07-26 5 3 olivier@huggingface.co david.richard.holtz@gmail.com
tracing.py
in server/text_generation_server
44 3 2023-03-07 2024-06-25 2 2 olivier@huggingface.co kevin.duffy94@gmail.com
__init__.py
in server/text_generation_server/utils
41 - 2023-03-07 2023-08-03 4 2 olivier@huggingface.co patry.nicolas@protonmail.com
bloom.py
in server/text_generation_server/models
37 3 2023-03-07 2024-07-05 28 7 olivier@huggingface.co patry.nicolas@protonmail.com
interceptor.py
in server/text_generation_server
32 1 2023-03-07 2024-10-16 4 2 olivier@huggingface.co olivier@huggingface.co
pyproject.toml
in clients/python
26 - 2023-03-07 2025-04-14 17 6 olivier@huggingface.co patry.nicolas@protonmail.com
cache.py
in server/text_generation_server
24 6 2023-03-07 2023-07-06 4 1 olivier@huggingface.co olivier@huggingface.co
__init__.py
in clients/python/text_generation
16 - 2023-03-07 2024-07-26 7 4 olivier@huggingface.co david.richard.holtz@gmail.com
__init__.py
in server/text_generation_server
1 - 2023-03-07 2023-03-07 1 1 olivier@huggingface.co olivier@huggingface.co
app.rs
in benchmark/src
464 10 2023-03-30 2024-09-24 8 6 olivier@huggingface.co orhunparmaksiz@gmail.com
generation.rs
in benchmark/src
186 1 2023-03-30 2024-11-15 17 5 olivier@huggingface.co me@danieldk.eu
main.rs
in benchmark/src
137 2 2023-03-30 2024-11-22 10 3 olivier@huggingface.co olivier@huggingface.co
lib.rs
in benchmark/src
126 - 2023-03-30 2024-09-24 9 5 olivier@huggingface.co orhunparmaksiz@gmail.com
event.rs
in benchmark/src
43 - 2023-03-30 2024-09-24 3 3 olivier@huggingface.co orhunparmaksiz@gmail.com
Cargo.toml
in benchmark
27 - 2023-03-30 2024-09-24 10 4 olivier@huggingface.co orhunparmaksiz@gmail.com
utils.rs
in benchmark/src
26 - 2023-03-30 2024-06-17 2 2 olivier@huggingface.co me@danieldk.eu
flash_causal_lm.py
in server/text_generation_server/models
2009 19 2023-04-03 2025-05-06 106 10 olivier@huggingface.co mohit21sharma.ms@gmail.com
flash_santacoder_modeling.py
in server/text_generation_server/models/custom_modeling
444 15 2023-04-03 2024-10-24 48 6 olivier@huggingface.co me@danieldk.eu
flash_neox_modeling.py
in server/text_generation_server/models/custom_modeling
339 12 2023-04-03 2024-10-24 43 7 olivier@huggingface.co me@danieldk.eu
__init__.py
in server/text_generation_server/models/custom_modeling
1 - 2023-04-03 2023-04-03 1 1 olivier@huggingface.co olivier@huggingface.co
flash_llama_modeling.py
in server/text_generation_server/models/custom_modeling
581 14 2023-04-11 2025-01-17 63 10 olivier@huggingface.co yi.a.wang@intel.com
build.rs
in router
18 1 2023-04-18 2023-05-02 3 2 olivier@huggingface.co patry.nicolas@protonmail.com
env_runtime.rs
in launcher/src
58 4 2023-05-02 2025-06-12 5 4 patry.nicolas@protonmail.com yuan.wu@intel.com
build.rs
in launcher
19 1 2023-05-02 2023-05-02 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
Files Not Recently Changed (Top 50)
File# lines# unitscreatedlast modified# changes
(days)
# contributorsfirst
contributor
latest
contributor
__init__.py
in server/text_generation_server
1 - 2023-03-07 2023-03-07 1 1 olivier@huggingface.co olivier@huggingface.co
errors.py
in clients/python/text_generation
61 12 2023-03-07 2023-03-07 1 1 olivier@huggingface.co olivier@huggingface.co
__init__.py
in server/text_generation_server/models/custom_modeling
1 - 2023-04-03 2023-04-03 1 1 olivier@huggingface.co olivier@huggingface.co
build.rs
in router
18 1 2023-04-18 2023-05-02 3 2 olivier@huggingface.co patry.nicolas@protonmail.com
build.rs
in launcher
19 1 2023-05-02 2023-05-02 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
fused_attention_cuda.cu
in server/custom_kernels/custom_kernels
219 - 2023-06-08 2023-06-08 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
cache.py
in server/text_generation_server
24 6 2023-03-07 2023-07-06 4 1 olivier@huggingface.co olivier@huggingface.co
tuning.h
in server/exllama_kernels/exllama_kernels
9 - 2023-07-21 2023-07-21 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
cuda_buffers.cuh
in server/exllama_kernels/exllama_kernels
40 - 2023-07-21 2023-07-21 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
column_remap.cu
in server/exllama_kernels/exllama_kernels/cuda_func
50 - 2023-07-21 2023-07-21 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
cuda_buffers.cu
in server/exllama_kernels/exllama_kernels
62 - 2023-07-21 2023-07-21 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
matrix.cuh
in server/exllama_kernels/exllama_kernels
250 - 2023-07-21 2023-07-21 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
__init__.py
in server/text_generation_server/utils
41 - 2023-03-07 2023-08-03 4 2 olivier@huggingface.co patry.nicolas@protonmail.com
watermark.py
in server/text_generation_server/utils
70 6 2023-03-07 2023-08-16 5 2 olivier@huggingface.co patry.nicolas@protonmail.com
util.h
in server/exllamav2_kernels/exllamav2_kernels/cpp
10 - 2023-11-25 2023-11-25 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
compat.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
45 - 2023-11-25 2023-11-25 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
qdq_3.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
146 - 2023-11-25 2023-11-25 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
speculate.py
in server/text_generation_server/utils
7 2 2023-12-11 2023-12-11 1 2 23298448+olivierdehaene@use... patry.nicolas@protonmail.com
config.h
in server/exllamav2_kernels/exllamav2_kernels
11 - 2023-11-25 2023-12-21 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_util.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
44 - 2023-11-25 2023-12-21 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q_matrix.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
57 - 2023-11-25 2023-12-21 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
ext.cpp
in server/exllamav2_kernels/exllamav2_kernels
115 - 2023-11-25 2023-12-21 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q_gemm_kernel.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
507 - 2023-11-25 2023-12-21 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
util.cuh
in server/exllama_kernels/exllama_kernels
25 - 2023-07-21 2024-01-26 2 2 patry.nicolas@protonmail.com 9808326+fxmarty@users.norep...
cu_compat.cuh
in server/exllama_kernels/exllama_kernels
46 - 2024-01-26 2024-01-26 1 1 9808326+fxmarty@users.norep... 9808326+fxmarty@users.norep...
q_gemm_kernel_gptq.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
231 - 2023-11-25 2024-02-09 3 3 patry.nicolas@protonmail.com 57442720+ilyasmoutawwakil@u...
q4_matmul.cuh
in server/exllama_kernels/exllama_kernels/cuda_func
31 - 2023-07-21 2024-02-12 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q4_matrix.cu
in server/exllama_kernels/exllama_kernels/cuda_func
166 - 2023-07-21 2024-02-12 3 3 patry.nicolas@protonmail.com olivier@huggingface.co
q_gemm.cu
in server/exllamav2_kernels/exllamav2_kernels/cuda
198 - 2023-11-25 2024-02-12 3 2 patry.nicolas@protonmail.com olivier@huggingface.co
exllama_ext.cpp
in server/exllama_kernels/exllama_kernels
198 3 2023-07-21 2024-02-12 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q4_matmul.cu
in server/exllama_kernels/exllama_kernels/cuda_func
218 - 2023-07-21 2024-02-12 4 4 patry.nicolas@protonmail.com olivier@huggingface.co
q_matrix.cu
in server/exllamav2_kernels/exllamav2_kernels/cuda
544 - 2023-11-25 2024-02-12 4 3 patry.nicolas@protonmail.com olivier@huggingface.co
column_remap.cuh
in server/exllama_kernels/exllama_kernels/cuda_func
15 - 2023-07-21 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_8.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
29 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q_gemm.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
31 - 2023-11-25 2024-02-16 3 2 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_6.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
33 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
q4_matrix.cuh
in server/exllama_kernels/exllama_kernels/cuda_func
37 - 2023-07-21 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
util.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
45 - 2023-11-25 2024-02-16 3 2 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_2.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
89 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
matrix_view.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda
104 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
idefics_config.py
in server/text_generation_server/models/custom_modeling
144 4 2023-08-17 2024-02-16 3 3 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_5.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
184 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
qdq_4.cuh
in server/exllamav2_kernels/exllamav2_kernels/cuda/quant
195 - 2023-11-25 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
fused_bloom_attention_cuda.cu
in server/custom_kernels/custom_kernels
219 - 2023-06-08 2024-02-16 2 2 patry.nicolas@protonmail.com olivier@huggingface.co
convert.py
in server/text_generation_server/utils
82 3 2023-03-07 2024-04-05 10 3 olivier@huggingface.co patry.nicolas@protonmail.com
conv.py
in server/text_generation_server/layers
33 2 2024-05-13 2024-05-13 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
conversion_utils.py
in server/text_generation_server/layers/awq
46 4 2024-05-13 2024-05-13 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
hip_compat.cuh
in server/exllama_kernels/exllama_kernels
45 - 2024-01-26 2024-05-17 3 2 9808326+fxmarty@users.norep... 9808326+fxmarty@users.norep...
chunks.py
in server/text_generation_server/utils
17 1 2024-05-31 2024-05-31 1 1 me@danieldk.eu me@danieldk.eu
proto
208 - 2022-10-11 2024-06-04 33 5 olivier@huggingface.co olivier@huggingface.co
Most Recently Created Files (Top 50)
File# lines# unitscreatedlast modified# changes
(days)
# contributorsfirst
contributor
latest
contributor
flash_gemma3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
629 20 2025-06-19 2025-06-23 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
flash_qwen3_moe_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
405 16 2025-06-13 2025-06-23 2 2 yuan.wu@intel.com yi.a.wang@intel.com
tgi_env.py
in backends/neuron/server/text_generation_server
229 7 2025-06-10 2025-06-10 1 1 david.corvoysier@gmail.com david.corvoysier@gmail.com
tgi_entry_point.py
in backends/neuron
34 1 2025-06-10 2025-06-10 1 1 david.corvoysier@gmail.com david.corvoysier@gmail.com
w8an_fp.py
in backends/gaudi/server/text_generation_server/layers/compressed_tensors
209 7 2025-05-28 2025-05-28 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
loader.py
in backends/gaudi/server/text_generation_server/layers/compressed_tensors
115 9 2025-05-28 2025-05-28 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
__init__.py
in backends/gaudi/server/text_generation_server/layers/compressed_tensors
2 - 2025-05-28 2025-05-28 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
flash_qwen3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
302 8 2025-05-23 2025-06-23 3 2 yuan.wu@intel.com yi.a.wang@intel.com
flash_llama4_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
1116 53 2025-05-15 2025-06-23 6 2 yuan.wu@intel.com yi.a.wang@intel.com
flash_vlm_causal_lm.py
in backends/gaudi/server/text_generation_server/models
856 30 2025-04-14 2025-06-19 13 3 yi.a.wang@intel.com yi.a.wang@intel.com
flash_mllama.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
748 31 2025-04-14 2025-06-12 3 1 yi.a.wang@intel.com yi.a.wang@intel.com
qwen2_5_vl.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
724 25 2025-04-14 2025-06-12 2 2 yi.a.wang@intel.com yi.a.wang@intel.com
flash_deepseek_v3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
604 16 2025-04-14 2025-06-23 4 1 yi.a.wang@intel.com yi.a.wang@intel.com
idefics3.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
467 23 2025-04-14 2025-06-18 3 2 yi.a.wang@intel.com 15324346+regisss@users.nore...
qwen2_vl.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
429 16 2025-04-14 2025-06-12 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
fp8.py
in backends/gaudi/server/text_generation_server/layers/moe
240 9 2025-04-14 2025-05-19 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
flash_llava_next.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
201 9 2025-04-14 2025-06-18 3 2 yi.a.wang@intel.com 15324346+regisss@users.nore...
hpu.py
in backends/gaudi/server/text_generation_server/layers/attention
178 10 2025-04-14 2025-06-11 5 1 yi.a.wang@intel.com yi.a.wang@intel.com
hpu.py
in backends/gaudi/server/text_generation_server/layers/gptq
163 9 2025-04-14 2025-04-14 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
kv_cache.py
in backends/gaudi/server/text_generation_server/layers/attention
138 13 2025-04-14 2025-05-22 3 1 yi.a.wang@intel.com yi.a.wang@intel.com
hpu.py
in backends/gaudi/server/text_generation_server/layers/awq/quantize
99 8 2025-04-14 2025-04-14 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
fused_moe.py
in backends/gaudi/server/text_generation_server/layers/moe
97 3 2025-04-14 2025-05-19 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
prefill_chunking.py
in backends/gaudi/server/text_generation_server/utils
15 4 2025-04-14 2025-04-14 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
kernels.py
in backends/gaudi/server/text_generation_server/utils
12 1 2025-04-14 2025-04-14 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
__init__.py
in backends/gaudi/server/text_generation_server/layers/awq/quantize
2 - 2025-04-14 2025-04-14 1 1 yi.a.wang@intel.com yi.a.wang@intel.com
transformers_flash_vlm.py
in server/text_generation_server/models
499 15 2025-04-06 2025-05-06 3 2 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
flash_gemma3_modeling.py
in server/text_generation_server/models/custom_modeling
724 21 2025-03-12 2025-05-06 4 2 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
chat.rs
in router/src
641 7 2025-03-12 2025-03-12 1 1 patry.nicolas@protonmail.com patry.nicolas@protonmail.com
image_processing_gemma3.py
in server/text_generation_server/models/custom_modeling/gemma3
300 4 2025-03-12 2025-03-18 2 1 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
processing_gemma3.py
in server/text_generation_server/models/custom_modeling/gemma3
137 5 2025-03-12 2025-03-18 2 1 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
configuration_gemma3.py
in server/text_generation_server/models/custom_modeling/gemma3
113 2 2025-03-12 2025-03-12 1 1 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
utils.py
in server/text_generation_server/models/custom_modeling/gemma3
26 2 2025-03-12 2025-03-12 1 1 mohit21sharma.ms@gmail.com mohit21sharma.ms@gmail.com
quantize.rs
in backends/llamacpp/src
30 - 2025-03-11 2025-03-11 1 1 angt@huggingface.co angt@huggingface.co
llamacpp.rs
in backends/llamacpp/src
5 - 2025-03-11 2025-03-11 1 1 angt@huggingface.co angt@huggingface.co
flash_causal_lm.py
in backends/gaudi/server/text_generation_server/models
2113 26 2025-02-28 2025-06-19 15 4 32412211+baptistecolle@user... yi.a.wang@intel.com
__init__.py
in backends/gaudi/server/text_generation_server/models
984 2 2025-02-28 2025-06-19 9 3 32412211+baptistecolle@user... yi.a.wang@intel.com
quantize.py
in backends/gaudi/server/text_generation_server/layers/gptq
855 32 2025-02-28 2025-04-14 2 2 32412211+baptistecolle@user... yi.a.wang@intel.com
seq2seq_lm.py
in backends/gaudi/server/text_generation_server/models
737 10 2025-02-28 2025-04-14 2 2 32412211+baptistecolle@user... yi.a.wang@intel.com
idefics2.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
677 30 2025-02-28 2025-06-18 4 3 32412211+baptistecolle@user... 15324346+regisss@users.nore...
bloom_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
652 22 2025-02-28 2025-04-14 2 2 32412211+baptistecolle@user... yi.a.wang@intel.com
tokens.py
in backends/gaudi/server/text_generation_server/utils
634 27 2025-02-28 2025-05-06 2 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_dbrx_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
614 24 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_rw_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
578 18 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_llama_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
555 14 2025-02-28 2025-06-23 6 3 32412211+baptistecolle@user... yi.a.wang@intel.com
mllama_causal_lm.py
in backends/gaudi/server/text_generation_server/models
546 11 2025-02-28 2025-06-18 11 3 32412211+baptistecolle@user... 15324346+regisss@users.nore...
flash_deepseek_v2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
543 13 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
fp8.py
in backends/gaudi/server/text_generation_server/layers
528 23 2025-02-28 2025-05-28 4 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_starcoder2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
515 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
rotary.py
in backends/gaudi/server/text_generation_server/layers
507 24 2025-02-28 2025-06-23 5 3 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_gemma2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
492 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
Most Recently Changed Files (Top 50)
File# lines# unitscreatedlast modified# changes
(days)
# contributorsfirst
contributor
latest
contributor
flash_llama4_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
1116 53 2025-05-15 2025-06-23 6 2 yuan.wu@intel.com yi.a.wang@intel.com
flash_gemma3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
629 20 2025-06-19 2025-06-23 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
flash_dbrx_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
614 24 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_deepseek_v3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
604 16 2025-04-14 2025-06-23 4 1 yi.a.wang@intel.com yi.a.wang@intel.com
flash_rw_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
578 18 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_llama_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
555 14 2025-02-28 2025-06-23 6 3 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_deepseek_v2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
543 13 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_starcoder2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
515 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
rotary.py
in backends/gaudi/server/text_generation_server/layers
507 24 2025-02-28 2025-06-23 5 3 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_gemma2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
492 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_mistral_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
422 11 2025-02-28 2025-06-23 6 3 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_mixtral_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
422 17 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_cohere_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
422 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_qwen3_moe_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
405 16 2025-06-13 2025-06-23 2 2 yuan.wu@intel.com yi.a.wang@intel.com
flash_gemma_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
401 15 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_phi_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
363 13 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_neox_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
344 12 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_qwen2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
333 12 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_gptj_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
330 13 2025-02-28 2025-06-23 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_qwen3_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
302 8 2025-05-23 2025-06-23 3 2 yuan.wu@intel.com yi.a.wang@intel.com
flash_causal_lm.py
in backends/gaudi/server/text_generation_server/models
2113 26 2025-02-28 2025-06-19 15 4 32412211+baptistecolle@user... yi.a.wang@intel.com
__init__.py
in backends/gaudi/server/text_generation_server/models
984 2 2025-02-28 2025-06-19 9 3 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_vlm_causal_lm.py
in backends/gaudi/server/text_generation_server/models
856 30 2025-04-14 2025-06-19 13 3 yi.a.wang@intel.com yi.a.wang@intel.com
generator.py
in backends/neuron/server/text_generation_server
501 43 2025-02-24 2025-06-19 4 3 david.corvoysier@gmail.com david@huggingface.co
model.py
in backends/gaudi/server/text_generation_server/models
111 7 2025-02-28 2025-06-19 3 2 32412211+baptistecolle@user... yi.a.wang@intel.com
vlm.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
55 2 2025-02-28 2025-06-19 3 2 32412211+baptistecolle@user... yi.a.wang@intel.com
Cargo.toml
in root
49 - 2022-10-18 2025-06-19 67 10 olivier@huggingface.co david@huggingface.co
idefics2.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
677 30 2025-02-28 2025-06-18 4 3 32412211+baptistecolle@user... 15324346+regisss@users.nore...
mllama_causal_lm.py
in backends/gaudi/server/text_generation_server/models
546 11 2025-02-28 2025-06-18 11 3 32412211+baptistecolle@user... 15324346+regisss@users.nore...
idefics3.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
467 23 2025-04-14 2025-06-18 3 2 yi.a.wang@intel.com 15324346+regisss@users.nore...
flash_llava_next.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
201 9 2025-04-14 2025-06-18 3 2 yi.a.wang@intel.com 15324346+regisss@users.nore...
segments.py
in backends/gaudi/server/text_generation_server/utils
38 4 2025-02-28 2025-06-18 2 2 32412211+baptistecolle@user... 15324346+regisss@users.nore...
debug.py
in backends/gaudi/server/text_generation_server/utils
29 3 2025-02-28 2025-06-13 2 2 32412211+baptistecolle@user... yi.a.wang@intel.com
main.rs
in launcher/src
1815 35 2022-10-18 2025-06-12 137 21 olivier@huggingface.co yuan.wu@intel.com
flash_mllama.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
748 31 2025-04-14 2025-06-12 3 1 yi.a.wang@intel.com yi.a.wang@intel.com
qwen2_5_vl.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
724 25 2025-04-14 2025-06-12 2 2 yi.a.wang@intel.com yi.a.wang@intel.com
qwen2_vl.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
429 16 2025-04-14 2025-06-12 2 1 yi.a.wang@intel.com yi.a.wang@intel.com
cli.py
in backends/gaudi/server/text_generation_server
297 3 2025-02-28 2025-06-12 5 3 32412211+baptistecolle@user... yuan.wu@intel.com
flash_pali_gemma_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
98 4 2025-02-28 2025-06-12 3 2 32412211+baptistecolle@user... yi.a.wang@intel.com
env_runtime.rs
in launcher/src
58 4 2023-05-02 2025-06-12 5 4 patry.nicolas@protonmail.com yuan.wu@intel.com
pyproject.toml
in backends/gaudi/server
38 - 2025-02-28 2025-06-12 4 3 32412211+baptistecolle@user... yuan.wu@intel.com
globals.py
in backends/gaudi/server/text_generation_server/models
33 3 2025-02-28 2025-06-12 3 3 32412211+baptistecolle@user... yuan.wu@intel.com
flash_santacoder_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
442 15 2025-02-28 2025-06-11 4 2 32412211+baptistecolle@user... yi.a.wang@intel.com
flash_gpt2_modeling.py
in backends/gaudi/server/text_generation_server/models/custom_modeling
366 15 2025-02-28 2025-06-11 4 2 32412211+baptistecolle@user... yi.a.wang@intel.com
hpu.py
in backends/gaudi/server/text_generation_server/layers/attention
178 10 2025-04-14 2025-06-11 5 1 yi.a.wang@intel.com yi.a.wang@intel.com
__init__.py
in backends/gaudi/server/text_generation_server/layers/attention
30 - 2025-02-28 2025-06-11 5 2 32412211+baptistecolle@user... yi.a.wang@intel.com
tgi_env.py
in backends/neuron/server/text_generation_server
229 7 2025-06-10 2025-06-10 1 1 david.corvoysier@gmail.com david.corvoysier@gmail.com
model.py
in backends/neuron/server/text_generation_server
99 4 2025-02-24 2025-06-10 3 2 david.corvoysier@gmail.com david.corvoysier@gmail.com
tgi_entry_point.py
in backends/neuron
34 1 2025-06-10 2025-06-10 1 1 david.corvoysier@gmail.com david.corvoysier@gmail.com
fp8.py
in backends/gaudi/server/text_generation_server/layers
528 23 2025-02-28 2025-05-28 4 2 32412211+baptistecolle@user... yi.a.wang@intel.com