Skip to content

Actions: amritahs-ibm/llama.cpp

Actions

Python Type-Check

Actions

Loading...
Loading

Show workflow options

Create status badge

Loading
python-type-check.yml
21 workflow runs
21 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

server : include speculative decoding stats when timings_per_token is… Python Type-Check #21: Commit 5d01670 pushed by amritahs-ibm
1m 25s master
master
1m 25s
clip: Fix llama-llava-clip-quantize-cli quantization error under CUDA… Python Type-Check #20: Commit 02082f1 pushed by amritahs-ibm
1m 24s master
master
1m 24s
sycl: cleanup oneDNN related code (#12097) Python Type-Check #19: Commit 9ffcc9e pushed by amritahs-ibm
1m 22s master
master
1m 22s
llamafile_sgemm for int4 Python Type-Check #18: Commit 910ac5e pushed by amritahs-ibm
16m 35s sgemm_q4
sgemm_q4
16m 35s
server (webui): Fix Premature Submission During IME Conversion (#11971) Python Type-Check #17: Commit c392e50 pushed by amritahs-ibm
1m 23s master
master
1m 23s
vulkan: linux builds + small subgroup size fixes (#11767) Python Type-Check #16: Commit a4f011e pushed by amritahs-ibm
1m 13s master
master
1m 13s
sync: minja (#11499) Python Type-Check #15: Commit 3d804de pushed by amritahs-ibm
1m 9s master
master
1m 9s
GEMV implementation Python Type-Check #14: Commit 4418c26 pushed by amritahs-ibm
1m 27s gemv
gemv
1m 27s
Vulkan-run-test: fix mmq_wg_denoms (#11343) Python Type-Check #13: Commit 955a6c2 pushed by amritahs-ibm
1m 19s master
master
1m 19s
ggml : fixes for AVXVNNI instruction set with MSVC and Clang (#11027) Python Type-Check #12: Commit 0827b2c pushed by amritahs-ibm
6m 41s master
master
6m 41s
llamafile_sgemm API - INT8 implementation Python Type-Check #11: Commit a8d3700 pushed by amritahs-ibm
3m 46s sgemm_q8
sgemm_q8
3m 46s
server : add support for "encoding_format": "base64" to the */embeddi… Python Type-Check #10: Commit 9ba399d pushed by amritahs-ibm
1m 11s master
master
1m 11s
llamafile_sgemm API - INT8 implementation Python Type-Check #9: Commit 3c60b12 pushed by amritahs-ibm
1m 13s sgemm_q8
sgemm_q8
1m 13s
llamafile_sgemm API - INT8 implementation Python Type-Check #8: Pull request #4 synchronize by amritahs-ibm
1m 26s sgemm_int8
sgemm_int8
1m 26s
llamafile_sgemm API - INT8 implementation Python Type-Check #7: Commit d83a8aa pushed by amritahs-ibm
1m 17s sgemm_int8
sgemm_int8
1m 17s
ggml : fix row condition for i8mm kernels (#10561) Python Type-Check #6: Commit 76b27d2 pushed by amritahs-ibm
1m 27s master
master
1m 27s
cmake : fix ppc64 check (whisper/0) Python Type-Check #5: Commit 09ecbcb pushed by amritahs-ibm
1m 30s master
master
1m 30s
ggml : move CPU backend to a separate file (#10144) Python Type-Check #4: Commit 9f40989 pushed by amritahs-ibm
1m 14s origin/master
origin/master
1m 14s
flake.lock: Update (#10063) Python Type-Check #3: Commit 07028f9 pushed by amritahs-ibm
37m 48s master
master
37m 48s
Sgemm ppc mma Python Type-Check #2: Pull request #2 opened by amritahs-ibm
4m 23s sgemm_ppc_mma
sgemm_ppc_mma
4m 23s
PPC MMA implementation Python Type-Check #1: Commit 46dcd2b pushed by amritahs-ibm
1m 13s sgemm_ppc_mma
sgemm_ppc_mma
1m 13s