Skip to content

Actions: amritahs-ibm/llama.cpp

Actions

Server

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
server.yml
35 workflow runs
35 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Code refactor Server #35: Pull request #8 synchronize by amritahs-ibm
11m 39s code_refactor
code_refactor
11m 39s
Code refactor Server #34: Pull request #8 opened by amritahs-ibm
3m 53s code_refactor
code_refactor
3m 53s
server : include speculative decoding stats when timings_per_token is… Server #33: Commit 5d01670 pushed by amritahs-ibm
15m 46s master
master
15m 46s
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA… Server #32: Commit 02082f1 pushed by amritahs-ibm
9m 9s master
master
9m 9s
sycl: cleanup oneDNN related code (#12097) Server #31: Commit 9ffcc9e pushed by amritahs-ibm
12m 38s master
master
12m 38s
llamafile_sgemm for int4 Server #30: Pull request #7 synchronize by amritahs-ibm
8m 36s sgemm_q4
sgemm_q4
8m 36s
llamafile_sgemm for int4 Server #29: Pull request #7 synchronize by amritahs-ibm
4m 47s sgemm_q4
sgemm_q4
4m 47s
llamafile_sgemm for int4 Server #28: Pull request #7 synchronize by amritahs-ibm
24m 48s sgemm_q4
sgemm_q4
24m 48s
server (webui): Fix Premature Submission During IME Conversion (#11971) Server #27: Commit c392e50 pushed by amritahs-ibm
16m 44s master
master
16m 44s
llamafile_sgemm for int4 Server #26: Pull request #7 opened by amritahs-ibm
19m 1s sgemm_q4
sgemm_q4
19m 1s
vulkan: linux builds + small subgroup size fixes (#11767) Server #25: Commit a4f011e pushed by amritahs-ibm
8m 34s master
master
8m 34s
GEMV implementation Server #24: Pull request #6 synchronize by amritahs-ibm
18m 56s gemv
gemv
18m 56s
sync: minja (#11499) Server #23: Commit 3d804de pushed by amritahs-ibm
9m 15s master
master
9m 15s
GEMV implementation Server #22: Pull request #6 opened by amritahs-ibm
36m 38s gemv
gemv
36m 38s
server : add more clean up when cancel_tasks is called (#11340) Server #21: Commit 5845661 pushed by amritahs-ibm
28m 36s master
master
28m 36s
GEMV implementation Server #20: Pull request #5 synchronize by amritahs-ibm
24m 22s gemv
gemv
24m 22s
Vulkan-run-test: fix mmq_wg_denoms (#11343) Server #19: Commit 955a6c2 pushed by amritahs-ibm
8m 31s master
master
8m 31s
GEMV implementation Server #18: Pull request #5 opened by amritahs-ibm
10m 0s gemv
gemv
10m 0s
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027) Server #17: Commit 0827b2c pushed by amritahs-ibm
9m 31s master
master
9m 31s
server : add support for "encoding_format": "base64" to the */embeddi… Server #16: Commit 9ba399d pushed by amritahs-ibm
5m 30s master
master
5m 30s
llamafile_sgemm API - INT8 implementation Server #15: Pull request #4 synchronize by amritahs-ibm
4m 27s sgemm_int8
sgemm_int8
4m 27s
llamafile_sgemm API - INT8 implementation Server #14: Pull request #4 synchronize by amritahs-ibm
2m 4s sgemm_int8
sgemm_int8
2m 4s
llamafile_sgemm API - INT8 implementation Server #13: Pull request #4 synchronize by amritahs-ibm
9m 8s sgemm_int8
sgemm_int8
9m 8s
llamafile_sgemm API - INT8 implementation Server #12: Pull request #4 synchronize by amritahs-ibm
4m 29s sgemm_int8
sgemm_int8
4m 29s
llamafile_sgemm API - INT8 implementation Server #11: Pull request #4 synchronize by amritahs-ibm
3m 5s sgemm_int8
sgemm_int8
3m 5s